Marine disaster risk prevention and control early warning system

Abstract

The invention discloses a marine disaster risk prevention and control early warning system, which comprises a control center, a data acquisition unit, a data transmission unit, a data processing and analysis unit, an early warning model construction unit and an early warning release unit, a signal channel of the control center communicates with signal channels of the data acquisition unit, the data processing and analysis unit, the early warning model construction unit and the early warning issuing unit through the data transmission unit. By integrating the multi-source sensor network and the advanced remote sensing technology, all-directional, multi-dimensional and high-precision real-time monitoring of the marine environment can be realized, the monitoring coverage range is greatly expanded, the data acquisition efficiency and precision are improved, and the real-time monitoring of the marine environment can be realized by constructing a set of efficient early warning model. The models can deeply mine potential laws and relevance in data, the occurrence probability and the possible influence range of marine disasters are accurately predicted, continuous learning and optimization are achieved, and the accuracy and timeliness of the early warning model are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of marine disaster early warning, and in particular to a marine disaster risk prevention and control early warning system. Background Art

[0002] Marine disasters refer to disasters that endanger human life and property in the ocean due to changes in the natural environment of the ocean or improper human intervention. Marine disasters are mainly divided into two categories: sudden and slow. Sudden marine disasters have great direct harm and usually cause significant damage in a short period of time. Common sudden marine disasters include storm surges, tsunamis, high waves, dense fog, red tides, etc. Storm surge: a disaster caused by a large amount of seawater caused by a strong storm rushing towards the land; Tsunami: a large-scale wave caused by an undersea earthquake, undersea landslide or volcanic eruption; High waves: huge waves caused by strong sea breezes or storms, which will have a serious impact on the coastline and marine facilities; Dense fog: fog on the ocean will seriously affect navigation safety, reduce visibility, and cause ship accidents; Red tide: eutrophication of the ocean leads to the massive reproduction of algae, which changes the color of the sea water and may pose a threat to marine life and human health.

[0003] With global climate change and increased marine activities, marine disasters such as storm surges, tsunamis, sea ice, and red tides are occurring frequently, posing a serious threat to the safety of life and property in coastal areas. Traditional marine disaster early warning systems often rely on a single data source and simple prediction models, making it difficult to comprehensively and accurately assess disaster risks.

[0004] Therefore, we propose an early warning system for marine disaster risk prevention and control. Summary of the invention

[0005] The purpose of the present invention is to provide a marine disaster risk prevention and control early warning system to solve the problems raised in the background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a marine disaster risk prevention and control early warning system, comprising a control center, a data acquisition unit, a data transmission unit, a data processing and analysis unit, an early warning model construction unit and an early warning release unit, wherein the signal channel of the control center is interconnected with the signal channels of the data acquisition unit, the data processing and analysis unit, the early warning model construction unit and the early warning release unit respectively through the data transmission unit;

[0007] The data acquisition unit includes multi-source sensors, remote sensing satellites and drones. The multi-source sensors are used to monitor sea temperature, salinity, flow velocity, wind direction and speed, wave height and seabed topography. The remote sensing satellites and drones use high-resolution remote sensing satellites and drones to perform large-scale, high-frequency remote sensing monitoring of the marine environment to obtain information on sea surface temperature, chlorophyll concentration and sea ice distribution.

[0008] The data transmission unit is a wireless data transmission module, which transmits the collected data to the control center in real time for processing and analysis;

[0009] The data processing and analysis unit includes a data processing module and a data analysis module. The data processing module is used to clean, integrate and store massive data, and the data analysis module is used to perform feature extraction, pattern recognition and trend prediction on marine environment data.

[0010] The early warning model construction unit is used to construct an early warning model based on a convolutional neural network algorithm, train the model using historical disaster data and real-time monitoring data, receive monitoring data from multi-source sensors in real time, and output disaster prediction results;

[0011] The warning issuing unit is a warning issuing module, which is used to issue warning information.

[0012] As a preferred embodiment of the present invention, the early warning model based on the convolutional neural network algorithm is specifically:

[0013] Step 1: Data preprocessing: convert the data collected by the data acquisition unit into image form for processing by the convolutional neural network; perform preprocessing operations such as normalization and denoising on the image data to improve the training effect of the model;

[0014] Step 2: Feature extraction: Use the convolution kernel in the convolution layer to perform convolution operations on the image to extract local features in the image. Downsample the feature map through the pooling layer to reduce the amount of calculation and retain important features. Repeat the convolution and pooling operations to build a deep convolutional neural network structure to extract higher-level features.

[0015] Step 3: Model training: Use a large amount of historical disaster data and real-time monitoring data to train the convolutional neural network, optimize the network parameters through the back propagation algorithm, so that the model can accurately identify the characteristics of marine disasters. During the training process, use data enhancement technology to increase the diversity of training samples and improve the generalization ability of the model;

[0016] Step 4: Disaster prediction, real-time receiving of monitoring data from multi-source sensors, and converting it into image form and inputting it into the model. The model extracts and classifies the input image features and outputs the disaster prediction results.

[0017] As a preferred implementation of the present invention, the wireless data transmission module specifically uses LoRa, NB-IoT low-power wide area network or satellite communication technology for data transmission.

[0018] As a preferred implementation manner of the present invention, the multi-source sensor is specifically a temperature sensor, a conductivity sensor, a flow meter, an anemometer, a wind vane, a wave sensor, and a sonar sensor.

[0019] As a preferred embodiment of the present invention, the convolutional layer in the convolutional neural network is used to extract local features of the input data, and the calculation formula of the convolutional layer is:

[0020] N = (W-F+2P) / S+1;

[0021] in:

[0022] N is the size of the output feature map;

[0023] W is the size of the input feature map;

[0024] F is the size of the convolution kernel;

[0025] P is the padding size, which is used to add extra pixel values ​​at the boundary of the input feature map to control the size of the output feature map;

[0026] S is the stride, which indicates the number of pixels that the convolution kernel moves on the input feature map.

[0027] As a preferred implementation of the present invention, the warning release module specifically releases warning information through official websites, mobile phone APPs, social media, text messages, and broadcast channels.

[0028] As a preferred implementation manner of the present invention, the control center further includes a database, and the database is used to store data.

[0029] As a preferred implementation of the present invention, the control center further includes a data updating module, and the data updating module is used to regularly clean up expired data and release space.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] By integrating multi-source sensor networks and advanced remote sensing technology, the present invention can realize all-round, multi-dimensional, high-precision real-time monitoring of the marine environment. This comprehensive monitoring system not only covers traditional marine observation methods, such as buoys, submerged buoys, seabed-based observation stations, etc., but also makes full use of emerging technologies such as satellite remote sensing, drone inspections, and underwater unmanned vehicles, thereby greatly expanding the coverage of monitoring and improving data collection efficiency and accuracy. By constructing a set of efficient early warning models, these models can deeply explore the potential laws and correlations in the data, accurately predict the probability of occurrence and possible impact range of marine disasters, and through continuous learning and optimization, the accuracy and timeliness of the early warning model have been significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0033] Figure 1 This is an operation diagram of a marine disaster risk prevention and control early warning system of the present invention. DETAILED DESCRIPTION

[0034] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0035] Example

[0036] A marine disaster risk prevention and control early warning system, comprising a control center, a data acquisition unit, a data transmission unit, a data processing and analysis unit, an early warning model building unit and an early warning issuing unit;

[0037] The data acquisition unit includes multi-source sensors, remote sensing satellites and drones. Multi-source sensors are used to monitor sea temperature, salinity, current velocity, wind direction and speed, wave height and seabed topography. Remote sensing satellites and drones use high-resolution remote sensing satellites and drones to conduct large-scale, high-frequency remote sensing monitoring of the marine environment to obtain information on sea surface temperature, chlorophyll concentration and sea ice distribution. Multi-source sensors are specifically temperature sensors, conductivity sensors, current meters, anemometers, wind vanes, wave sensors and sonar sensors.

[0038] in:

[0039] Monitoring of sea temperature

[0040] Meteorological satellites are used to measure the radiation emitted by the ocean and sea surfaces in the infrared atmospheric window, and the sea surface temperature is calculated using the Planck formula;

[0041] Buoys deployed on the sea surface or sensors on the seabed can also monitor sea temperature changes in real time.

[0042] Salinity monitoring

[0043] The conductivity method, refractive index method, laser speckle method and other methods are used to measure the conductivity of seawater, the refractive index of light or the laser scattering intensity with sensors, so as to infer the salinity of seawater.

[0044] Flow rate

[0045] The velocity of seawater is calculated using instruments such as a current meter or an acoustic Doppler current profiler (ADCP) by measuring the impact of water flow on the device or the speed at which sound signals propagate in water.

[0046] Wind direction and speed

[0047] Anemometers and wind vanes deployed on the sea surface or on the shore can monitor wind direction and speed in real time.

[0048] Wave height

[0049] The built-in sensors of the wave buoy are used to monitor wave height, wave period, wave direction and other parameters in real time.

[0050] Seafloor topography

[0051] High-precision topographic measurements of the seabed are carried out using multi-beam bathymetric systems, side-scan sonar and other equipment.

[0052] The data transmission unit is a wireless data transmission module, which transmits the collected data to the control center in real time for processing and analysis; the wireless data transmission module specifically uses LoRa, NB-IoT low-power wide area network or satellite communication technology for data transmission.

[0053] The control center also includes a database, which is used to store data;

[0054] The control center also includes a data update module, which is used to regularly clean up expired data and release space.

[0055] The data processing and analysis unit includes a data processing module and a data analysis module. The data processing module is used to clean, integrate and store massive data, and the data analysis module is used to extract features, identify patterns and predict trends of marine environmental data.

[0056] The early warning model building unit is used to build an early warning model based on a convolutional neural network algorithm, train the model using historical disaster data and real-time monitoring data, receive monitoring data from multi-source sensors in real time, and output disaster prediction results;

[0057] The warning release unit is a warning release module, which is used to release warning information, specifically through official websites, mobile APPs, social media, text messages, and broadcast channels.

[0058] It should be noted that:

[0059] The early warning model based on the convolutional neural network algorithm is as follows:

[0060] Step 1: Data preprocessing: convert the data collected by the data acquisition unit into image form for processing by the convolutional neural network; perform preprocessing operations such as normalization and denoising on the image data to improve the training effect of the model;

[0061] Step 2: Feature extraction: Use the convolution kernel in the convolution layer to perform convolution operations on the image to extract local features in the image. Downsample the feature map through the pooling layer to reduce the amount of calculation and retain important features. Repeat the convolution and pooling operations to build a deep convolutional neural network structure to extract higher-level features.

[0062] Among them: The convolution layer in the convolutional neural network is used to extract the local features of the input data. The calculation formula of the convolution layer is:

[0063] N = (W-F+2P) / S+1;

[0064] in:

[0065] N is the size of the output feature map;

[0066] W is the size of the input feature map;

[0067] F is the size of the convolution kernel;

[0068] P is the padding size, which is used to add extra pixel values ​​at the boundary of the input feature map to control the size of the output feature map;

[0069] S is the stride, which indicates the number of pixels that the convolution kernel moves on the input feature map.

[0070] Step 3: Model training: Use a large amount of historical disaster data and real-time monitoring data to train the convolutional neural network, optimize the network parameters through the back propagation algorithm, so that the model can accurately identify the characteristics of marine disasters. During the training process, use data enhancement technology to increase the diversity of training samples and improve the generalization ability of the model;

[0071] Step 4: Disaster prediction, real-time receiving of monitoring data from multi-source sensors, and converting it into image form and inputting it into the model. The model extracts and classifies the input image features and outputs the disaster prediction results.

[0072] In summary, the present invention can realize all-round, multi-dimensional, high-precision real-time monitoring of the marine environment by integrating multi-source sensor networks and advanced remote sensing technology. This comprehensive monitoring system not only covers traditional marine observation methods, such as buoys, submerged buoys, seabed-based observation stations, etc., but also makes full use of emerging technologies such as satellite remote sensing, drone inspections, and underwater unmanned vehicles, thereby greatly expanding the coverage of monitoring and improving data collection efficiency and accuracy. By constructing a set of efficient early warning models, these models can deeply explore the potential laws and correlations in the data, accurately predict the probability of occurrence and possible impact range of marine disasters, and through continuous learning and optimization, the accuracy and timeliness of the early warning model have been significantly improved.

[0073] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention.

[0074] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A marine disaster risk prevention and control early warning system, characterized in that: It includes a control center, a data acquisition unit, a data transmission unit, a data processing and analysis unit, an early warning model construction unit and an early warning release unit, wherein the signal channel of the control center is interconnected with the signal channels of the data acquisition unit, the data processing and analysis unit, the early warning model construction unit and the early warning release unit respectively through the data transmission unit; The data acquisition unit includes multi-source sensors, remote sensing satellites and drones. The multi-source sensors are used to monitor sea temperature, salinity, flow velocity, wind direction and speed, wave height and seabed topography. The remote sensing satellites and drones use high-resolution remote sensing satellites and drones to perform large-scale, high-frequency remote sensing monitoring of the marine environment to obtain information on sea surface temperature, chlorophyll concentration and sea ice distribution. The data transmission unit is a wireless data transmission module, which transmits the collected data to the control center in real time for processing and analysis; The data processing and analysis unit includes a data processing module and a data analysis module. The data processing module is used to clean, integrate and store massive data, and the data analysis module is used to perform feature extraction, pattern recognition and trend prediction on marine environment data. The early warning model construction unit is used to construct an early warning model based on a convolutional neural network algorithm, train the model using historical disaster data and real-time monitoring data, receive monitoring data from multi-source sensors in real time, and output disaster prediction results; The warning issuing unit is a warning issuing module, which is used to issue warning information.

2. A marine disaster risk prevention and control early warning system according to claim 1, characterized in that: The early warning model based on the convolutional neural network algorithm is specifically: Step 1: Data preprocessing: convert the data collected by the data acquisition unit into image form for processing by the convolutional neural network; perform preprocessing operations such as normalization and denoising on the image data to improve the training effect of the model; Step 2: Feature extraction: Use the convolution kernel in the convolution layer to perform convolution operations on the image to extract local features in the image. Downsample the feature map through the pooling layer to reduce the amount of calculation and retain important features. Repeat the convolution and pooling operations to build a deep convolutional neural network structure to extract higher-level features. Step 3: Model training: Use a large amount of historical disaster data and real-time monitoring data to train the convolutional neural network, optimize the network parameters through the back propagation algorithm, so that the model can accurately identify the characteristics of marine disasters. During the training process, use data enhancement technology to increase the diversity of training samples and improve the generalization ability of the model; Step 4: Disaster prediction, real-time receiving of monitoring data from multi-source sensors, and converting it into image form and inputting it into the model. The model extracts and classifies the input image features and outputs the disaster prediction results.

3. The marine disaster risk prevention and control early warning system according to claim 1 is characterized by: The wireless data transmission module specifically uses LoRa, NB-IoT low-power wide area network or satellite communication technology for data transmission.

4. The marine disaster risk prevention and control early warning system according to claim 1 is characterized by: The multi-source sensor is specifically a temperature sensor, a conductivity sensor, a flow meter, an anemometer, a wind vane, a wave sensor, and a sonar sensor.

5. A marine disaster risk prevention and control early warning system according to claim 2, characterized in that: The convolutional layer in the convolutional neural network is used to extract local features of the input data. The calculation formula of the convolutional layer is: N = (W-F+2P) / S+1; in: N is the size of the output feature map; W is the size of the input feature map; F is the size of the convolution kernel; P is the padding size, which is used to add extra pixel values ​​at the boundary of the input feature map to control the size of the output feature map; S is the stride, which indicates the number of pixels that the convolution kernel moves on the input feature map.

6. The marine disaster risk prevention and control early warning system according to claim 1 is characterized by: The warning release module specifically releases warning information through official websites, mobile APPs, social media, text messages, and broadcast channels.

7. The marine disaster risk prevention and control early warning system according to claim 1 is characterized by: The control center also includes a database, and the database is used to store data.

8. The marine disaster risk prevention and control early warning system according to claim 1 is characterized by: The control center also includes a data update module, which is used to regularly clean up expired data and release space.

Images