CN114638441A - Ocean current monitoring and early warning system based on satellite remote sensing image - Google Patents
Ocean current monitoring and early warning system based on satellite remote sensing image Download PDFInfo
- Publication number
- CN114638441A CN114638441A CN202210536744.XA CN202210536744A CN114638441A CN 114638441 A CN114638441 A CN 114638441A CN 202210536744 A CN202210536744 A CN 202210536744A CN 114638441 A CN114638441 A CN 114638441A
- Authority
- CN
- China
- Prior art keywords
- ocean current
- early warning
- data
- user
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C13/00—Surveying specially adapted to open water, e.g. sea, lake, river or canal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/1851—Systems using a satellite or space-based relay
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Radar, Positioning & Navigation (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Remote Sensing (AREA)
- Game Theory and Decision Science (AREA)
- Environmental & Geological Engineering (AREA)
- Astronomy & Astrophysics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Development Economics (AREA)
- Emergency Management (AREA)
- Geology (AREA)
- Multimedia (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
Abstract
The invention relates to an ocean current monitoring and early warning system based on a satellite remote sensing image; the early warning system includes: the user terminal is configured to receive at least one implementation item of a user from the user, use relevant data of the implementation item for analyzing the attention index C, and send early warning information to the user after receiving the early warning information of the early warning terminal; the early warning terminal is configured to acquire ocean current data from a plurality of information sources and predict the change values of a plurality of ocean current elements according to the monitoring data; and further, comparing the change value of the ocean current element with the attention index C of the user, and determining the target sending user generating the early warning information and the early warning information. The early warning system effectively utilizes ocean current elements highly related to the user to calculate whether the current ocean current changes have a change trend highly related to the user or not, and performs early warning operation, so that personalized early warning demand service for the user is more efficiently achieved.
Description
Technical Field
The invention relates to ocean current monitoring technology. Particularly, the invention relates to an ocean current monitoring and early warning system based on a satellite remote sensing image.
Background
The ocean current disaster prevention can be directly used for ocean economic activities, and when ocean transportation, ocean scientific investigation, ocean oil development, ocean military activities and aquaculture activities are influenced by sea waves, serious disasters can be caused to the ocean activities. The efficient and reliable sea wave detection and prediction technology can effectively prevent sudden disasters of sea waves, and is an important guarantee for marine economy and military activities. At present, ocean current monitoring and early warning technology mainly acquires and forecasts ocean wave information in a traditional observation mode by combining with a statistical theory, and the forecasted ocean current information is mostly an ocean wave spectrum formed by large-range statistical data; furthermore, as the ocean current development is frequently changed along with the climate change in recent years, a great amount of theories and deduction models which need to be updated exist in past statistical data, so that the difficulty in predicting the ocean current information becomes high. Meanwhile, with the increase of activities of people on the ocean surface in recent years, the requirement on the space-time precision of ocean current prediction is high, the influence of ocean current on a specific project needs to be judged more pertinently according to various production activities, and data information provided by traditional ocean current monitoring and forecasting cannot meet the requirement.
By referring to related published technical schemes, the technical scheme with the publication number of CN216207432U provides an ocean current motion prediction algorithm based on a BP neural network prediction model, which can predict the ocean current motion rapidly, improve the accuracy of the ocean current motion prediction and improve the accuracy of the ocean current motion prediction; the technical solution of publication No. US20160203696a1 proposes a technique for sensing abnormal tidal level fluctuation for monitoring tsunami, in which an estimate of sea surface fluctuation is obtained by performing statistical processing or test processing on tsunami physical phenomena displayed in image information. The abnormal tidal fluctuation detection apparatus according to the present invention is configured to: detecting from within the video the position of an object or horizon that fluctuates in association with tidal level, and detecting that the position fluctuates in a time period that is different from the time period of tides or ocean waves; the technical scheme of publication number JP2018503833A includes a plurality of radio wave detection and ranging devices, a synchronization source and a processing device, and the objects in the marine environment are synchronously detected by the plurality of radio wave detection and ranging devices, so that the real-time monitoring of ocean current changes is realized. The prior art provides the functions of observing ocean current changes from a macroscopic view and giving a certain delayed alarm, however, economic production projects implemented by users in the ocean are various, and a personalized early warning system is needed to give targeted ocean current monitoring and early warning.
The foregoing discussion of the background art is intended only to facilitate an understanding of the present invention. This discussion is not an acknowledgement or admission that any of the material referred to is part of the common general knowledge.
Disclosure of Invention
The invention aims to provide an ocean current monitoring and early warning system based on a satellite remote sensing image; the early warning system includes: the user terminal is configured to receive at least one implementation item of a user from the user, use relevant data of the implementation item for analyzing the attention index C, and send early warning information to the user after receiving the early warning information of the early warning terminal; the early warning terminal is configured to acquire ocean current data from a plurality of information sources and predict the change values of a plurality of ocean current elements according to the monitoring data; and further, comparing the change value of the ocean current element with the attention index C of the user, and determining the target sending user generating the early warning information and the early warning information. The early warning system effectively utilizes ocean current elements highly related to the user to calculate whether the current ocean current changes have a change trend highly related to the user or not, and performs early warning operation, so that personalized early warning demand service for the user is more efficiently achieved.
The invention adopts the following technical scheme:
an ocean current monitoring and early warning system based on satellite remote sensing images, the early warning system includes:
the early warning system comprises a user terminal, a data processing module and a data processing module, wherein the user terminal is configured to receive at least one implementation project of a user from the user, use related data of the implementation project for analyzing an attention index C, and after receiving an early warning target of the early warning terminal, generate early warning information comprising the early warning target and related ocean current data, confirm the user of the implementation project represented by the early warning target, and send the early warning information to the user;
the early warning terminal is configured to acquire ocean current data from a plurality of information sources and predict the change values of a plurality of ocean current elements according to the monitoring data; comparing the change value of the ocean current element with the attention index C of the user, determining to generate early warning information and sending the early warning information to the user;
wherein, early warning terminal includes:
the data acquisition module is used for acquiring historical ocean current data and real-time ocean current data;
the data analysis module is used for analyzing the ocean current data obtained by the data acquisition module and analyzing and predicting future predicted values of a plurality of ocean current elements on the basis of a probability prediction model; the predicted values of the ocean current elements are further compared with the safety range of the attention index C, and one or more implementation projects with the predicted values exceeding the safety range are marked as early warning targets;
the early warning information issuing module: the early warning system is used for sending information of one or more early warning targets to the user terminal;
optionally, the user terminal includes:
the input module is used for providing interaction with a user, inputting information data of an implementation project of the user and recording the affiliation relationship between the user and the implementation project related to the user;
the processing module is used for calculating the attention index C of each implementation project for the user implementation project information data collected by the input module;
the communication module is used for carrying out communication connection between the user terminal and the early warning terminal to carry out data transmission;
the output module is configured to determine the belonged user according to one implementation project and send the early warning information to the user;
optionally, the input module obtains a latitude and longitude range of a sea area of the implementation project of the user, and sets the latitude and longitude range as a focus range; and obtaining a value or range of values for one or more ocean current elements that may affect the implementation as E = (E)1,E2……En) (ii) a The ocean current elements at least comprise: ocean current temperature, flow velocity, flow direction, salinity and seawater pressure;
further, the attention index C is calculated by:
in the formula 1, EiFor a plurality of said ocean current elements, ωiAs a weight coefficient corresponding to each of said ocean current elements, biA correction value for each of said ocean current elements; above omegaiAnd biEvaluating the implementation items by related technicians to obtain the evaluation results;
optionally, the data acquisition module comprises a plurality of acquisition sub-modules, at least comprising:
the first submodule is used for acquiring historical ocean current data based on time sequence and real-time or quasi-real-time dynamic ocean current data from the existing ocean analysis product; wherein the historical ocean current data comprises a year-by-day background flow field model, wherein the background flow field model comprises a plurality of ocean current elements;
the second sub-module is used for calculating a turning flow field of each attention range by utilizing real-time data of a satellite altimeter based on a plurality of attention ranges;
a third sub-module for calculating an Ecman flow field for each of said ranges of interest using satellite scatterometer real-time data based on a plurality of said ranges of interest;
performing data analysis, data fusion and inverse operation on the turning field and the Ekerman flow field to obtain a real-time inverse-operation ocean current model;
optionally, the data analysis module comprises an ocean current database for recording the ocean current data obtained by the data acquisition module and historical data obtained from existing ocean analysis products; the first submodule calls required ocean current data from the ocean current database;
optionally, the data analysis module further comprises a probabilistic predictive model based on a convolutional neural network, and the training and verification of the probabilistic predictive model are performed by using historical ocean current data;
wherein the data acquisition module inputs real-time or quasi-real-time dynamic ocean current data acquired by the first sub-module, data of a current field acquired by the second sub-module, and data of an Ekman current field acquired by the third sub-module to the data analysis module; the item category of the data input to the data analysis module by the data acquisition module comprises part, all or more than the ocean current elements E = (E)1,E2……En) The item of (1);
obtaining each ocean current element E from the output of the probability prediction model1,E2……EnPrediction set of [ E ]1]、[E2]……[En](ii) a The prediction set includes j predicted values for each of the ocean current elements and a probability corresponding to each predicted value, namely [ E1]=[(e11,pe11),(e12,pe12)……(e1j,pe1j)]Wherein e is11、e12……e1jI.e. corresponding to said ocean current element E1A set of j predicted values ofThe prediction probability p includes pe11、pe12……pe1jI.e. the prediction probability corresponding to each prediction value; and the value of the prediction probability p is constrained by the following equation 2:
in formula 2, the predicted value with probability less than 0.1 is ignored;
optionally, the continuous predicted value output by the probabilistic predictive model is discretized, so that the continuous predicted value is discretized into a plurality of predicted values at equal intervals, thereby obtaining a limited number of predicted values.
Optionally, the probabilities of multiple predicted values and corresponding predicted values of each ocean current element are counted to obtain one ocean current element EnExpected value of Q (E)i)：
wherein e isikI.e. ocean current element eiThe kth prediction value of peikI.e. corresponding to the eikA prediction probability of a predicted value;
by obtaining expected values Q (E) of a plurality of said ocean current elementsi) I =1, 2 … … n, and the corresponding ocean current element E in formula 1iReplacement by Q (E)i) Calculating to obtain an expected attention coefficient Q (C); when the attention coefficient Q (C) is expected to exceed a safety interval (C)max,Cmin) If yes, generating early warning information of implementation items based on the attention index C; wherein the upper limit value C of the safety intervalmaxAnd a lower limit value CminSet by the user and the associated technician.
The beneficial effects obtained by the invention are as follows:
1. the early warning system disclosed by the invention utilizes a large amount of historical ocean current data to generate a probability prediction model based on a neural network, and the output prediction value is calculated and utilized with emphasis according to the probability condition, so that the defect of predicting one-sidedness caused by ocean current variability is effectively overcome;
2. the early warning system inputs real-time or quasi-real-time satellite data into the probability prediction model for prediction, is different from the conventional monitoring and early warning mode that a large amount of data needs to be counted for calculating multiple ocean current elements, is properly balanced in the aspects of prediction effect and timeliness, and improves the early warning prospect;
3. the early warning system provided by the invention is based on ocean current elements which need to be concerned by the implementation project of the user, and ignores the data part with lower importance, so that the data quantity of operation and prediction is increased, and the efficiency of the early warning system is improved;
4. the positioning system adopts modularized design and cooperation of all parts, and can be flexibly optimized and changed through software and hardware in the later period, so that a large amount of later maintenance and upgrading cost is saved.
Drawings
The invention will be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
FIG. 1 is a schematic diagram of the early warning system of the present invention;
FIG. 2 is a schematic flow chart of the data analysis module of the present invention for processing ocean current data;
FIG. 3 is a schematic diagram illustrating the detecting and positioning principles of a second detecting device in the positioning method according to the present invention;
FIG. 4 is a schematic diagram of the early warning by marking the attention area and the surrounding sea area in different forms according to the embodiment of the present invention;
fig. 5 is a schematic diagram of an ocean current prediction image of the image monitoring system according to the embodiment of the present invention.
Reference numerals in the drawings indicate: 100-a user terminal; 101-an input module; 102-a communication module; 103-an output module; 110-early warning terminal; 111-a data acquisition module; 112-a data analysis module; 113-early warning information issuing module.
Detailed Description
In order to make the technical solution and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the embodiments thereof; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Other systems, methods, and/or features of the present embodiments will become apparent to one with skill in the art upon examination of the following detailed description. It is intended that all such additional systems, methods, features and advantages be included within this description, be within the scope of the invention, and be protected by the accompanying claims. Additional features of the disclosed embodiments are described in, and will be apparent from, the detailed description that follows.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it is to be understood that if there is an orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", etc. based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not intended to indicate or imply that the device or assembly referred to must have a specific orientation.
The first embodiment is as follows:
the ocean project implemented by the user at present has wide related scope, and ocean current elements related to the ocean project are more; at present, most users can only observe and analyze data based on the existing ocean current analysis products, so that early warning with certain effect is realized; however, the implementation method has certain delay, and most non-professional users are difficult to determine data highly related to implementation projects of the non-professional users for analysis when facing a lot of data due to the lack of an effective analysis method;
therefore, this embodiment provides an ocean current monitoring and early warning system based on satellite remote sensing images, as shown in fig. 1, the early warning system includes:
the system comprises a user terminal 100, a data processing module and a data processing module, wherein the user terminal 100 is configured to receive at least one implementation project of a user from the user, use relevant data of the implementation project for analyzing an attention index C, and after receiving an early warning target of an early warning terminal 110, generate the early warning target and early warning information including relevant ocean current data, confirm the user of the implementation project represented by the early warning target, and send the early warning information to the user;
an early warning terminal 110 configured to acquire ocean current data from a plurality of information sources and predict a variation value of a plurality of ocean current elements from the monitoring data; furthermore, comparing the change value of the ocean current element with the attention index C of the user to determine the generation of the early warning information and the target sending user of the early warning information;
wherein, the early warning terminal 110 includes:
the data acquisition module 111 is used for acquiring historical ocean current data and real-time ocean current data;
a data analysis module 112, configured to analyze the ocean current data obtained by the data acquisition module 111, and analyze and predict future predicted values of a plurality of ocean current elements based on a probabilistic prediction model; the predicted values of the ocean current elements are further compared with the safety range of the attention index C, and one or more implementation projects with the predicted values exceeding the safety range are marked as early warning targets;
the early warning information release module 113: for transmitting information of one or more of the early warning targets to the user terminal 100;
optionally, the user terminal 100 includes:
the input module 101 is used for providing interaction with a user, inputting information data of an implementation project of the user and recording the affiliation relationship between the user and the implementation project related to the user;
the processing module is used for calculating the attention index C of each implementation project according to the user implementation project information data acquired by the input module 101;
a communication module 102, configured to perform communication connection between the user terminal 100 and the early warning terminal 110 to perform data transmission;
the output module 103 is configured to determine a user to which the user belongs according to an implementation project and send the early warning information to the user;
optionally, the input module 101 obtains a latitude and longitude range of a sea area of a user implementation project, and sets the latitude and longitude range as a focus range; and obtains a value or range of values for one or more ocean current elements that may affect the implementation as E = (E)1,E2……En) (ii) a The ocean current elements at least comprise: ocean current temperature, flow velocity, flow direction, salinity and seawater pressure;
further, the attention index C is calculated by:
in the formula 1, EiFor a plurality of said ocean current elements, ωiAs a weight coefficient corresponding to each of said ocean current elements, biA correction value for each of the ocean current elements; above omegaiAnd biEvaluating the implementation items by related technicians to obtain the evaluation results;
optionally, the data acquisition module 111 includes a plurality of acquisition sub-modules, including at least:
the first submodule is used for acquiring historical ocean current data based on time sequence and real-time or quasi-real-time dynamic ocean current data from the existing ocean analysis product; wherein the historical ocean current data comprises a year-by-day background flow field model, wherein the background flow field model comprises a plurality of ocean current elements;
the second sub-module is used for calculating a turning field of each concern range by utilizing real-time data of a satellite altimeter based on a plurality of concern ranges;
a third sub-module for calculating an Ecman flow field for each of said ranges of interest using satellite scatterometer real-time data based on a plurality of said ranges of interest;
performing data analysis, data fusion and inverse operation on the turning field and the Ekerman flow field to obtain a real-time inverse-operation ocean current model;
optionally, the data analysis module 112 includes an ocean current database for recording the ocean current data obtained by the data acquisition module 111 and historical data obtained from existing ocean analysis products; the first submodule calls required ocean current data from the ocean current database;
optionally, the data analysis module 112 further comprises a probabilistic prediction model based on a convolutional neural network, and the training and verification of the probabilistic prediction model are performed by using historical ocean current data;
wherein the data acquisition module 111 inputs, to the data analysis module 112, real-time or quasi-real-time dynamic ocean current data acquired by the first sub-module, data of the turning field acquired by the second sub-module, and data of the eggman flow field acquired by the third sub-module; the item category of the data input by the data acquisition module 111 to the data analysis module 112 includes part, all, or more than the ocean current element E = (E)1,E2……En) The item of (1);
obtaining each ocean current element E from the output of the probability prediction model1,E2……EnPrediction set of [ E ]1]、[E2]……[En](ii) a The prediction set includes j predicted values for each of the ocean current elements and a probability corresponding to each predicted value, namely [ E1]=[(e11,pe11),(e12,pe12)……(e1j,pe1j)]Wherein e is11、e12……e1jI.e. corresponding to said ocean current element E1A prediction probability p comprising pe11、pe12……pe1jI.e. the prediction probability corresponding to each predicted value; and the value of the prediction probability p is constrained by the following equation 2:
in formula 2, it is indicated that a prediction value having a probability of less than 0.1 is ignored;
optionally, discretizing the continuous predicted values output by the probability prediction model to enable the continuous predicted values to be discretized into a plurality of predicted values at equal intervals, so as to obtain a limited number of predicted values.
Optionally, the probabilities of multiple predicted values and corresponding predicted values of each ocean current element are counted to obtain one ocean current element EnExpected value of Q (E)i)：
by obtaining expected values Q (E) of a plurality of said ocean current elementsi) I =1, 2 … … n, and the corresponding ocean current element E in formula 1iReplacement by Q (E)i) Calculating to obtain an expected attention coefficient Q (C); when the attention coefficient Q (C) is expected to exceed a safety interval (C)max,Cmin) If yes, generating early warning information of implementation items based on the attention index C; wherein the upper limit value C of the safety intervalmaxAnd a lower limit value CminSetting by a user and a related technician;
optionally, the first sub-module comprises using existing marine products including China offshore and neighboring Sea ReAnalysis products (China Ocean ReAnalysis), South China Sea ReAnalysis products (A ReAnalysis dataset of the South China Sea), and Ocean ReAnalysis data set (An edge-penetrating Ocean ReAnalysis dataset for the joining area of Asia and Indian-Pacific Ocean) as Ocean current data sources; the method also comprises the steps of adopting historical data set data from Argo, WOD18, EN4 and the like; the marine analysis data product generally has certain delay due to statistics and processing of a large amount of marine data, but the reference value and the data value for prediction model training are high;
optionally, the second sub-module obtains a sea surface dynamic altitude field of the research interest area by adopting and fusing data of Jason-2 and HY-2 satellite altimeters, and calculates the ground transfer flow of the research sea area by using satellite altimeter data and corresponding sea surface dynamic altitude field average field data;
the third sub-module obtains a sea surface wind field in a research area by adopting and fusing ASCAT and HY-2 satellite scatterometer data, and calculates an air stress driven Ekman flow field by utilizing satellite scatterometer data.
Example two:
this embodiment should be understood to include at least all of the features of any of the foregoing embodiments and further modifications thereon;
in the past ocean current analysis technology division, most of the existing ocean current data are based on, historical data are compared, and the ocean current development trend is judged according to experience; this approach requires a prejudice by a technician who is very familiar with the laws of ocean current development and fails to give a probable probability data for the prejudice trend;
therefore, the embodiment includes a prediction model based on a probabilistic neural network; in other embodiments, the model can be established by using neural networks such as a CNN convolutional neural network, a BP back propagation neural network, an RNN recurrent neural network, and the like;
one embodiment of the present invention is as follows:
acquiring annual daily historical ocean current data as input data by the data acquisition module, inputting the input data into the input layer, and training the probability prediction model; in some embodiments, in order to improve training speed and efficiency, it is preferable to use historical ocean current data of a plurality of the attention areas and waters surrounding the attention areas as input data;
optionally, dividing the historical ocean current data, real-time or quasi-real-time ocean current data into water area grids at each 0.25 ° longitude x 0.25 ° latitude, and using the daily, or every 12 hours, or every 6 hours ocean current data as a data sample, namely a feature vector; each data sample comprises a plurality of ocean current elements, and each feature vector comprises a plurality of dimensions; each data sample comprises a plurality of partial or all numerical values of the ocean current elements;
further, as shown in fig. 2, a flow of processing ocean current data by the data analysis module includes data preprocessing before input of input data, including data cleaning and data normalization, and converting satellite remote sensing image data into floating point tensor and the like;
furthermore, the probability prediction model comprises a convolution layer and a pooling layer, and is used for further compressing the preprocessed input data so as to reduce the overfitting condition in the training of the prediction model;
the probabilistic neural network part is behind the pooling layer, as shown in FIG. 3; the probabilistic neural network comprises an input layer, a mode layer and a summation layer;
wherein the input layer is used for transmitting the feature vector into the network, the input layer comprises a plurality of neurons, the number of the neurons of the input layer is equal to the dimension of the feature vector, namely x is shown in fig. 31、x2……xn(ii) a The item category of the input data includes part, all, or more than the ocean current elements E = (E)1,E2……En) The item of (1);
further, a mode layer is arranged behind the input layer; the mode layer is a radial base layer; the number of neurons owned by the mode layer is equal to the number of samples used for training; each neuron of the mode layer has a center; the mode layer receives the input of the sample data of the input layer, calculates the distance between the characteristic vector of the input sample data and the center, namely calculates the matching degree of the characteristic vector of the sample data and the neuron in each mode layer, and finally returns a scalar value for representing the index of the matching degree with the neuron;
furthermore, a summing layer connects the mode layer units of each class, and the number of neurons of the summing layer is equal to the number of classes for classifying data, namely, the number of neurons of the summing layer is equal to the number of classes of the output value of one ocean current element; therefore, for the number of categories of the output values of one ocean current element, the degree of dispersion needs to be set first, for example, for the speed of the ocean current in the ocean current element, the number of categories is set to be one category per 0.1 m/s;
further, the summing layer counts matching degree indexes returned by the plurality of neurons in the mode layer and performs weighted summing; classifying sample data, comparing the sample data with each class, and calculating the similarity of comparison to obtain the probability value of one sample data, namely one eigenvector, in a plurality of output classes;
generally, the probabilistic neural network includes an output layer after the summation layer for outputting the class in which the probability value is the largest after being counted by the summation layer; in the embodiment, the output multiple categories and the probability value of each category are directly obtained from the summation layer;
with the above embodiment, after the probabilistic predictive model is built and trained, by inputting an ocean current data at the current time, a combination of predicted values of a plurality of ocean current elements at a future time, that is, the prediction set [ E ], can be obtained1]、[E2]……[En]And calculating expected values of a plurality of ocean current elements according to the formula 3, and further performing subsequent calculation.
Example three:
this embodiment should be understood to include at least all of the features of any of the foregoing embodiments and further modifications thereon;
in the continuous operation process of the early warning system, the data analysis module carries out periodic data analysis and sends early warning targets exceeding a safety threshold value to the user terminal in real time; the user terminals of a plurality of users receive all the early warning information, and the early warning information needing to be displayed can be set by the users based on factors such as concerned sea areas, implementation projects or ocean current elements;
in some embodiments, the output module provides a control interface for the user to collect and compile a plurality of the early warning information and the relevant sea area information thereof, and display the predicted ocean current information of the relevant sea area; in another aspect, further action may be taken by issuing the warning information to a user's mobile phone or providing a link to access the output module, thereby prompting the user to receive the warning information;
the early warning information can be filtered according to the sea area, or irrelevant early warning information is filtered by selecting a specific attention range of the ocean current elements; the user can know the early warning conditions of similar projects implemented in other sea areas or other users besides the implementation projects concerned by the user;
optionally, the output module includes a priority judgment sub-module and an auxiliary decision sub-module;
the priority judgment sub-module can select the most urgent early warning information according to one or more release criteria of the early warning information specified by the user, and perform continuous early warning or perform early warning representation on the user with stronger early warning strength, for example, the user is required to manually close the early warning information to ensure that the early warning information is personally read and known by the user; and the other common-level early warning information carries out conventional early warning;
as shown in fig. 4, different warning information or warning intensities of the warning information in different sea areas are displayed by marking relevant sea areas and surrounding sea areas with different forms, such as colors, symbols and the like;
optionally, the assistant decision sub-module may provide an additional information in real time to assist the user in making an adjustment decision for implementing the project according to the ocean current prediction data of the ocean current elements or the ocean current domains related to the early warning information, and update the priority order of the display of the early warning information according to the relevant criteria; for example, the assistant decision sub-module may be an image monitoring system, as shown in fig. 5, taking issuing an early warning message of a target sea area as an example, the data analysis module obtains a plurality of expected values Q (E)n) For example, the ocean current temperature is changed, but the ocean current flow velocity is not obviously changed; therefore, the aid decision-making module (video monitoring system) displays the ocean current temperature change condition of the sea area in the attention range of the user in a visual image in real time or displays the ocean current temperature change condition in the latest 24 hours past, and prompts the user for coping strategies;
in the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Although the invention has been described above with reference to various embodiments, it should be understood that many changes and modifications can be made without departing from the scope of the invention. That is, the methods, systems, and devices discussed above are examples. Various configurations may omit, substitute, or add various procedures or components as appropriate. For example, in alternative configurations, the methods may be performed in an order different than described, and/or various components may be added, omitted, and/or combined. Moreover, features described with respect to certain configurations may be combined in various other configurations, as different aspects and elements of the configurations may be combined in a similar manner. Further, elements therein may be updated as technology evolves, i.e., many elements are examples and do not limit the scope of the disclosure or claims.
Specific details are given in the description to provide a thorough understanding of the exemplary configurations including implementations. However, configurations may be practiced without these specific details, for example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary detail in order to avoid obscuring the configurations. This description provides example configurations only, and does not limit the scope, applicability, or configuration of the claims. Rather, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made in the function and arrangement of elements without departing from the spirit or scope of the disclosure.
In conclusion, it is intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that these examples are illustrative only and are not intended to limit the scope of the invention. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (10)
1. The utility model provides an ocean current monitoring and early warning system based on satellite remote sensing image which characterized in that, the system includes:
the early warning system comprises a user terminal, a data processing module and a data processing module, wherein the user terminal is configured to receive at least one implementation project of a user from the user, use related data of the implementation project for analyzing an attention index C, and after receiving an early warning target of the early warning terminal, generate early warning information comprising the early warning target and related ocean current data, confirm the user of the implementation project represented by the early warning target, and send the early warning information to the user;
the early warning terminal is configured to acquire ocean current data from a plurality of information sources and predict the change values of a plurality of ocean current elements according to the monitoring data; comparing the change value of the ocean current element with the attention index C of the user, determining to generate early warning information and sending the early warning information to the user;
wherein, early warning terminal includes:
the data acquisition module is used for acquiring historical ocean current data and real-time ocean current data;
the data analysis module is used for analyzing the ocean current data obtained by the data acquisition module and analyzing and predicting future predicted values of a plurality of ocean current elements on the basis of a probability prediction model; the predicted values of the ocean current elements are further compared with the safety range of the attention index C, and one or more implementation projects with the predicted values exceeding the safety range are marked as early warning targets;
the early warning information issuing module: and the system is used for sending information of one or more early warning targets to the user terminal.
2. The ocean current monitoring and early warning system based on satellite remote sensing images as claimed in claim 1, wherein the user terminal comprises:
the input module is used for providing interaction with a user, inputting information data of an implementation project of the user and recording the affiliation relationship between the user and the implementation project related to the user;
the processing module is used for calculating the attention index C of each implementation project for the user implementation project information data collected by the input module;
the communication module is used for carrying out communication connection and data transmission on the user terminal and the early warning terminal;
and the output module is configured to determine the belonged user according to one implementation item and send the early warning information to the user.
3. The ocean current monitoring and early warning system based on the satellite remote sensing image as claimed in claim 2, wherein the input module comprises a longitude and latitude range of a sea area for acquiring a user implementation project, and the longitude and latitude range is set as a focus range; and obtaining a value or range of values for one or more ocean current elements that may affect the implementation as E = (E)1,E2……En) (ii) a The ocean current elements at least comprise: ocean current temperature, flow rate, flow direction, salinity, seawater pressure.
4. The system according to claim 3, wherein the attention index C is calculated by the following steps:
in the formula 1, EiFor a plurality of said ocean current elements, ωiAs a weight coefficient corresponding to each of said ocean current elements, biA correction value for each of said ocean current elements; above omegaiAnd biThe evaluation results are obtained by carrying out multiple experimental evaluations on the implementation projects.
5. The ocean current monitoring and early warning system based on satellite remote sensing images as claimed in claim 4, wherein the data acquisition module comprises a plurality of acquisition sub-modules, at least comprising:
the first submodule is used for acquiring historical ocean current data based on time sequence and real-time or quasi-real-time dynamic ocean current data from the existing ocean analysis product; wherein the historical ocean current data comprises a year-by-day background flow field model, wherein the background flow field model comprises a plurality of ocean current elements;
the second sub-module is used for calculating a turning flow field of each attention range by utilizing real-time data of a satellite altimeter based on a plurality of attention ranges;
a third sub-module for calculating an Ecman flow field for each of said ranges of interest using satellite scatterometer real-time data based on a plurality of said ranges of interest;
and performing data analysis, data fusion and inverse operation on the turning field and the Ekerman flow field to obtain a real-time inverse-operation ocean current model.
6. The ocean current monitoring and early warning system based on the satellite remote sensing image as claimed in claim 5, wherein the data analysis module comprises an ocean current database for recording the ocean current data obtained by the data acquisition module and historical data obtained from existing ocean analysis products; the first submodule comprises a step of calling required ocean current data from the ocean current database.
7. The system of claim 6, wherein the data analysis module further comprises a probabilistic prediction model based on a convolutional neural network, and the probabilistic prediction model is trained and validated by using historical ocean current data.
8. The system according to claim 7, wherein the data acquisition module inputs real-time or quasi-real-time dynamic ocean current data acquired by the first submodule, data of a turning field acquired by the second submodule, and data of an Ekmann flow field acquired by the third submodule into the data analysis module; the item category of the data input to the data analysis module by the data acquisition module comprises part, all or more than the ocean current elements E = (E)1,E2……En) The item of (1);
obtaining each ocean current element E from the output of the probability prediction model1,E2……EnPrediction set of [ E ]1]、[E2]……[En](ii) a The prediction set includes j predicted values for each of the ocean current elements and a probability corresponding to each predicted value, i.e., [ E1]=[(e11,pe11),(e12,pe12)……(e1j,pe1j)]Wherein e is11、e12……e1jI.e. corresponding to said ocean current element E1A prediction probability p comprising pe11、pe12……pe1jI.e. the prediction probability corresponding to each prediction value; and the value of the prediction probability p is constrained by the following equation 2:
in equation 2, the predicted value having a probability of less than 0.1 is ignored.
9. The system of claim 8, wherein the continuous predicted values output by the probabilistic predictive model are discretized into a plurality of equally spaced predicted values, thereby obtaining a limited number of predicted values.
10. The system according to claim 9, wherein the probability between a plurality of predicted values and corresponding predicted values of each ocean current element is counted to obtain one ocean current element EnExpected value of Q (E)i)：
wherein e isikI.e. ocean current element eiTo (1) ak number of predictors, peikI.e. corresponding to the eikA prediction probability of the predicted value;
by obtaining expected values Q (E) of a plurality of said ocean current elementsi) I =1, 2 … … n, and the corresponding ocean current element E in formula 1iReplacement by Q (E)i) Calculating to obtain an expected attention coefficient Q (C); when the expected attention factor Q (C) exceeds a safety interval (C)max,Cmin) If yes, generating early warning information of implementation items based on the attention index C; wherein the upper limit value C of the safety intervalmaxAnd a lower limit value CminSet by the user and the associated technician.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210536744.XA CN114638441B (en) | 2022-05-18 | 2022-05-18 | Ocean current monitoring and early warning system based on satellite remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210536744.XA CN114638441B (en) | 2022-05-18 | 2022-05-18 | Ocean current monitoring and early warning system based on satellite remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114638441A true CN114638441A (en) | 2022-06-17 |
| CN114638441B CN114638441B (en) | 2022-08-16 |
Family
ID=81953302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210536744.XA Active CN114638441B (en) | 2022-05-18 | 2022-05-18 | Ocean current monitoring and early warning system based on satellite remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638441B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115728760A (en) * | 2022-11-22 | 2023-03-03 | 北京卫星信息工程研究所 | Tensor scattering information-based passive detection method for sea surface wind wave stream satellite |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070050142A1 (en) * | 2005-08-23 | 2007-03-01 | Pamela Posey | System and method for estimating ocean height and current on a personal computer with location adjustment |
| CN102394917A (en) * | 2011-10-19 | 2012-03-28 | 上海海洋大学 | Ocean environment monitoring and early warning system |
| CN106202163A (en) * | 2016-06-24 | 2016-12-07 | 中国环境科学研究院 | Tongjiang lake ecological monitoring information management and early warning system |
| CN106991491A (en) * | 2017-02-21 | 2017-07-28 | 南京邮电大学 | A kind of environment pollution monitoring system of the RBF neural based on genetic algorithm optimization |
| CN112099110A (en) * | 2020-09-17 | 2020-12-18 | 中国科学院海洋研究所 | Ocean internal wave forecasting method based on machine learning and remote sensing data |
| CN113138865A (en) * | 2020-08-10 | 2021-07-20 | 西安天和防务技术股份有限公司 | Environment monitoring method, system, platform and storage medium |
| CN113297801A (en) * | 2021-06-15 | 2021-08-24 | 哈尔滨工程大学 | Marine environment element prediction method based on STEOF-LSTM |
| US20220128358A1 (en) * | 2020-10-26 | 2022-04-28 | Burak Ozer | Smart Sensor Based System and Method for Automatic Measurement of Water Level and Water Flow Velocity and Prediction |
-
2022
- 2022-05-18 CN CN202210536744.XA patent/CN114638441B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070050142A1 (en) * | 2005-08-23 | 2007-03-01 | Pamela Posey | System and method for estimating ocean height and current on a personal computer with location adjustment |
| CN102394917A (en) * | 2011-10-19 | 2012-03-28 | 上海海洋大学 | Ocean environment monitoring and early warning system |
| CN106202163A (en) * | 2016-06-24 | 2016-12-07 | 中国环境科学研究院 | Tongjiang lake ecological monitoring information management and early warning system |
| CN106991491A (en) * | 2017-02-21 | 2017-07-28 | 南京邮电大学 | A kind of environment pollution monitoring system of the RBF neural based on genetic algorithm optimization |
| CN113138865A (en) * | 2020-08-10 | 2021-07-20 | 西安天和防务技术股份有限公司 | Environment monitoring method, system, platform and storage medium |
| CN112099110A (en) * | 2020-09-17 | 2020-12-18 | 中国科学院海洋研究所 | Ocean internal wave forecasting method based on machine learning and remote sensing data |
| US20220128358A1 (en) * | 2020-10-26 | 2022-04-28 | Burak Ozer | Smart Sensor Based System and Method for Automatic Measurement of Water Level and Water Flow Velocity and Prediction |
| CN113297801A (en) * | 2021-06-15 | 2021-08-24 | 哈尔滨工程大学 | Marine environment element prediction method based on STEOF-LSTM |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115728760A (en) * | 2022-11-22 | 2023-03-03 | 北京卫星信息工程研究所 | Tensor scattering information-based passive detection method for sea surface wind wave stream satellite |
| CN115728760B (en) * | 2022-11-22 | 2023-08-11 | 北京卫星信息工程研究所 | Sea surface storm satellite-borne passive detection method based on tensor scattering information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114638441B (en) | 2022-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047099B (en) | Regional torrential flood risk prediction method and system | |
| US11488069B2 (en) | Method for predicting air quality with aid of machine learning models | |
| CN112734694A (en) | Water quality monitoring method based on big data | |
| CN109086540B (en) | Method and device for constructing tropical cyclone path forecasting model | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| CN110738355A (en) | urban waterlogging prediction method based on neural network | |
| CN114638441B (en) | Ocean current monitoring and early warning system based on satellite remote sensing image | |
| CN115014299B (en) | Flood peak early warning method based on Internet of things and big data | |
| CN116539829A (en) | Water quality monitoring sensing analysis method | |
| Yao et al. | An improved deep learning model for high-impact weather nowcasting | |
| Essa et al. | Deep learning prediction of thunderstorm severity using remote sensing weather data | |
| Banerjee et al. | Traffic accident risk prediction using machine learning | |
| CN112991688A (en) | Geological disaster space-time combined early warning method and system based on PUL algorithm | |
| CN111178631B (en) | Water lettuce intrusion distribution area prediction method and system | |
| CN116110210B (en) | Data-driven landslide hazard auxiliary decision-making method in complex environment | |
| CN116665482A (en) | Parking space recommending method and device based on intelligent parking | |
| Porto et al. | Machine learning approaches to extreme weather events forecast in urban areas: Challenges and initial results | |
| CN113326728A (en) | Network anomaly detection method based on D-S evidence theory | |
| CN114722909A (en) | Solar flare time sequence classification method based on low-dimensional convolutional neural network | |
| Socaci et al. | XNow: A deep learning technique for nowcasting based on radar products’ values prediction | |
| Khaefi et al. | Nowcasting air quality by fusing insights from meteorological data, satellite imagery and social media images using deep learning | |
| CN113096445A (en) | Intelligent route design method using visual navigation mark as communication node | |
| Nguyen | Deep learning for tropical cyclone formation detection | |
| Bankert et al. | Remote cloud ceiling assessment using data-mining methods | |
| CN116384284B (en) | Red tide gridding forecasting method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |