Marine environment monitoring and early warning method and system based on big data

Abstract

The invention discloses a marine environment monitoring and early warning method and system based on big data, and relates to the technical field of marine environment monitoring, and the method comprises the steps: collecting environmental data in real time through a sensor in a monitoring station, and transmitting the environmental data to a database; acquiring the position information of each monitoring station by using a positioning technology, and calculating the distance between the randomly selected reference monitoring station and the corresponding comparison monitoring station; analyzing the change trend of the environment data, and determining the propagation speed of the abnormal environment data based on an analysis result; calculating the arrival time of the abnormal environment data propagated from the reference monitoring station to the comparison monitoring station by using a linear propagation algorithm in combination with the distance and the propagation speed; and setting alarm starting time according to the arrival time, and issuing alarm information. According to the invention, the real-time monitoring and data collection of the marine environment are realized through the deployment of the monitoring stations and the integrated sensor technology, and a comprehensive and accurate information basis is provided for subsequent data analysis and early warning.

Description

Technical Field

[0001] The present invention relates to the field of marine environment monitoring technology, and in particular to a marine environment monitoring and early warning method and system based on big data. Background Art

[0002] The marine environment, as a vast and interconnected area of ​​seawater on the earth, includes not only the seawater itself, but also various substances dissolved and suspended in it, seabed sediments, and the rich and diverse biological communities living in it. In order to ensure the sustainable use of marine resources and protect its ecological diversity, it is particularly important to implement systematic and continuous marine environmental monitoring and early warning. The system regularly checks and analyzes key parameters such as water temperature, salinity, water quality (such as nutrient concentration), oxygen levels, phytoplankton and animal population dynamics, benthic organisms, distribution of pollutants, and the impact of climate change. It can help scientists quickly identify any trends or patterns that deviate from the normal range, and make predictions based on this so that potential problems can be taken before they develop into serious crises.

[0003] With the advancement of science and technology, modern marine environment monitoring systems are able to collect more comprehensive and detailed information. These systems are usually composed of a variety of sensors and data acquisition equipment distributed in a vast sea area, monitoring key parameters such as water temperature, salinity, flow rate, and biological activity in real time. The data obtained is not only huge in quantity, but also diverse in type, covering everything from basic numerical values ​​to complex image and video information.

[0004] Faced with such a large and complex data set, traditional data processing methods often have difficulty in providing accurate and reliable analysis results and decision support information in a short period of time, which not only leads to delays in analysis and response, but may also hinder the timely release of early warning systems, thereby missing the best time to take timely and effective measures. This will significantly weaken the decision-makers' ability to respond quickly in emergencies, making it difficult to make accurate early warnings and effective responses to dynamic changes in the marine environment.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In response to the problems in the related technology, the present invention proposes a marine environment monitoring and early warning method and system based on big data to overcome the above-mentioned technical problems existing in the existing related technology.

[0007] To this end, the specific technical solution adopted by the present invention is as follows:

[0008] According to one aspect of the present invention, a method for monitoring and early warning of marine environment based on big data is provided, the method comprising the following steps:

[0009] S1. Deploy several monitoring stations in the marine environment monitoring area, collect environmental data in real time through sensors in the monitoring stations and transmit them to the database;

[0010] S2. Use positioning technology to obtain the location information of each monitoring site, and calculate the distance between the randomly selected benchmark monitoring site and the corresponding comparison monitoring site;

[0011] S3. Compare the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyze the changing trend of the environmental data, and determine the propagation speed of abnormal environmental data based on the analysis results;

[0012] S4, combining distance and propagation speed, using linear propagation algorithm to calculate the arrival time of abnormal environmental data from the reference monitoring site to the comparison monitoring site;

[0013] S5. Set the alarm start time according to the arrival time and issue the alarm information.

[0014] Furthermore, deploying several monitoring stations in the marine environment monitoring area, collecting environmental data in real time through sensors in the monitoring stations and transmitting the data to the database includes the following steps:

[0015] S11. Deploy several monitoring stations in the marine environment monitoring area according to the detection requirements, and configure corresponding sensors in each monitoring station;

[0016] S12, using sensors to collect environmental data in real time and pre-process the environmental data;

[0017] S13, fusing the pre-processed environmental data, and transmitting the fused environmental data to the database using wireless communication technology.

[0018] Furthermore, fusing the preprocessed environmental data and transmitting the fused environmental data to the database using wireless communication technology includes the following steps:

[0019] S131, extracting ocean environment parameters and ocean current information from the preprocessed environmental data;

[0020] S132, synchronizing the time series of ocean environment parameters and ocean current information to obtain the ocean environment parameters and ocean current information corresponding to each time point;

[0021] S133, using a Kalman filter algorithm to fuse the ocean environment parameters and ocean current information, wherein the ocean environment parameters and ocean current information are used as observation vectors, and through the prediction and update steps of the Kalman filter, the predicted state vector is gradually corrected to obtain fused environmental data;

[0022] S134, packaging the integrated environmental data according to a preset format, and using wireless communication technology to transmit the packaged environmental data to a database.

[0023] Furthermore, using positioning technology to obtain the location information of each monitoring site and calculating the distance between the randomly selected reference monitoring site and the corresponding comparison monitoring site includes the following steps:

[0024] S21, using positioning technology to deploy corresponding positioning equipment at each monitoring site, and obtaining location information of each monitoring site, where the location information of the monitoring site includes the longitude and latitude of the monitoring site;

[0025] S22. Randomly select a monitoring site from the monitoring sites as a benchmark monitoring site, and select a monitoring site adjacent to the benchmark monitoring site as a comparison monitoring site;

[0026] S23. Based on the location information of each monitoring site, the distance between the benchmark monitoring site and the comparison monitoring site is calculated using a geographic distance calculation formula.

[0027] Furthermore, the geographic distance calculation formula is:

[0028]

[0029] In the formula, D represents the distance between the benchmark monitoring site and the comparison monitoring site;

[0030] r represents the average radius of the Earth;

[0031] x1 represents the latitude of the benchmark monitoring site;

[0032] x2 represents the latitude of the comparison monitoring site;

[0033] y1 represents the longitude of the benchmark monitoring site;

[0034] y2 represents the longitude of the comparison monitoring site.

[0035] Furthermore, comparing the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyzing the change trend of the environmental data, and determining the propagation speed of the abnormal environmental data based on the analysis results includes the following steps:

[0036] S31, extracting historical standard environmental data of the benchmark monitoring site from the database;

[0037] S32, calculating the difference between the historical standard environmental data of the benchmark monitoring site and the environmental data collected in real time, and making a preliminary judgment on whether there is abnormal environmental data based on the preset difference;

[0038] S33, performing time series analysis on the real-time environmental data to analyze the change trend of the data, and determining abnormal environmental data in combination with the preliminary abnormality judgment result;

[0039] S34, establishing a spatial distribution data set based on the real-time environmental data of the comparative monitoring site, and applying a spatial analysis algorithm to extract the spatial distribution characteristics of the abnormal environmental data;

[0040] S35. Based on the spatial distribution characteristics of the abnormal environmental data and the time series analysis results, the propagation speed of the abnormal environmental data in the marine environment is calculated.

[0041] Furthermore, according to the real-time environmental data of the comparative monitoring sites, a spatial distribution data set is established, and the spatial distribution characteristics of the abnormal environmental data are extracted by applying a spatial analysis algorithm, including the following steps:

[0042] S341, obtaining environmental data of the comparative monitoring site, and using positioning technology to obtain location information of each comparative monitoring site;

[0043] S342, combining the environmental data and location information of the comparison monitoring site to establish a spatial distribution data set;

[0044] S343, analyzing the spatial distribution data set using a semivariance model, and interpolating within the spatial distribution data set to generate a spatial distribution map;

[0045] S344, combining the abnormal environment data with the spatial distribution map, estimating an estimated value of the abnormal environment data;

[0046] S345. Based on the estimated value of the abnormal environment data, extract the spatial distribution characteristics of the abnormal environment data.

[0047] Furthermore, the formula of the semivariance model is:

[0048]

[0049] Where T represents the estimated value of abnormal environmental data at latitude m and longitude n;

[0050] m represents the latitude of abnormal environmental data;

[0051] n represents the longitude of abnormal environmental data;

[0052] K represents the spatial distribution dataset;

[0053] k represents the real-time environmental data of the kth comparison monitoring site;

[0054] η represents the weight coefficient;

[0055] t represents time.

[0056] Furthermore, combining the distance and the propagation speed, the linear propagation algorithm is used to calculate the arrival time of the abnormal environmental data from the reference monitoring site to the comparison monitoring site, including the following steps:

[0057] S41, combining the distance between the reference monitoring site and the corresponding comparison monitoring site and the propagation speed of the abnormal environment data, using a linear propagation algorithm, calculating the propagation time required for the abnormal environment data to propagate from the reference monitoring site to the comparison monitoring site;

[0058] S42, obtaining the time when the abnormal environment data is at the reference monitoring site, integrating the propagation time, and calculating the arrival time when the abnormal environment data is propagated from the reference monitoring site to the comparison monitoring site.

[0059] According to another aspect of the present invention, there is also provided a marine environment monitoring and early warning system based on big data, the system comprising a data collection module, a position and distance calculation module, a propagation speed determination module, an arrival time calculation module and an alarm issuance module;

[0060] The data collection module is used to deploy several monitoring stations in the marine environment monitoring area, collect environmental data in real time through sensors in the monitoring stations and transmit them to the database;

[0061] The location and distance calculation module is used to obtain the location information of each monitoring site by using positioning technology, and calculate the distance between the randomly selected benchmark monitoring site and the corresponding comparison monitoring site;

[0062] A propagation speed determination module is used to compare the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyze the changing trend of the environmental data, and determine the propagation speed of the abnormal environmental data based on the analysis results;

[0063] The arrival time calculation module is used to combine the distance and propagation speed and use the linear propagation algorithm to calculate the arrival time of the abnormal environmental data from the reference monitoring site to the comparison monitoring site;

[0064] The alarm publishing module is used to set the alarm start time according to the arrival time and publish the alarm information.

[0065] The beneficial effects of the present invention are:

[0066] 1. The present invention realizes real-time monitoring and data collection of the marine environment by deploying monitoring stations and integrating sensor technology, which not only improves the timeliness and integrity of the data, but also uses data integration technology to integrate scattered data sources into a unified data set, thereby providing a comprehensive and accurate information basis for subsequent data analysis and early warning.

[0067] 2. By comparing the historical standard environmental data of the benchmark monitoring site with the real-time environmental data, the present invention can timely discover the changing trend of environmental data and identify abnormal data, which helps to more accurately judge the current environmental status, thereby improving the sensitivity and reliability of the early warning system.

[0068] 3. The present invention combines the distance between monitoring sites and the propagation speed of abnormal environmental data, and uses a linear propagation algorithm to calculate the estimated arrival time of abnormal data, providing a scientific basis for setting the alarm activation time. It can quickly identify and respond to potential environmental risks, effectively shorten the early warning response time, and thus improve the efficiency and effectiveness of emergency response. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 is a flow chart of a marine environment monitoring and early warning method based on big data according to an embodiment of the present invention;

[0071] Figure 2 It is a principle block diagram of a marine environment monitoring and early warning system based on big data according to an embodiment of the present invention.

[0072] In the figure:

[0073] 1. Data collection module; 2. Position and distance calculation module; 3. Propagation speed determination module; 4. Arrival time calculation module; 5. Alarm release module. DETAILED DESCRIPTION

[0074] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments. They can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention.

[0075] According to an embodiment of the present invention, a method and system for monitoring and early warning of marine environment based on big data are provided.

[0076] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the marine environment monitoring and early warning method based on big data according to an embodiment of the present invention, the method comprises the following steps:

[0077] S1. Deploy several monitoring stations in the marine environment monitoring area, collect environmental data in real time through sensors in the monitoring stations and transmit them to the database.

[0078] Specifically, deploying several monitoring stations in the marine environment monitoring area, collecting environmental data in real time through sensors in the monitoring stations and transmitting them to the database includes the following steps:

[0079] S11. According to the detection requirements, several monitoring stations are deployed in the marine environment monitoring area, and corresponding sensors are configured in each monitoring station.

[0080] S12. Use sensors to collect environmental data in real time and pre-process the environmental data.

[0081] It should be noted that environmental data includes meteorological data (wind speed, wind direction, etc.) and oceanographic data (wave height, etc.).

[0082] Preprocessing of environmental data includes: verifying the collected environmental data, checking whether the data is within a reasonable range, and whether there are abnormal values ​​or missing values. If abnormal values ​​or missing values ​​are found, they will be corrected or marked as invalid data; converting the verified environmental data into a unified format for subsequent processing and storage.

[0083] S13, fusing the pre-processed environmental data, and transmitting the fused environmental data to the database using wireless communication technology.

[0084] Specifically, fusing the preprocessed environmental data and transmitting the fused environmental data to the database using wireless communication technology includes the following steps:

[0085] S131. Extracting ocean environment parameters and ocean current information from the preprocessed environmental data.

[0086] It should be noted that ocean environmental parameters include wind speed, wind direction, and wave height; and ocean current information includes ocean current speed and direction.

[0087] S132, synchronizing the time series of ocean environment parameters and ocean current information to obtain the ocean environment parameters and ocean current information corresponding to each time point.

[0088] S133. Use the Kalman filter algorithm to fuse the ocean environment parameters and ocean current information, wherein the ocean environment parameters and ocean current information are used as observation vectors. Through the prediction and update steps of the Kalman filter, the predicted state vector is gradually corrected to obtain the fused environmental data.

[0089] S134, packaging the integrated environmental data according to a preset format, and using wireless communication technology to transmit the packaged environmental data to a database.

[0090] S2. Use positioning technology to obtain the location information of each monitoring site, and calculate the distance between the randomly selected benchmark monitoring site and the corresponding comparison monitoring site.

[0091] Specifically, using positioning technology to obtain the location information of each monitoring site and calculating the distance between a randomly selected reference monitoring site and a corresponding comparison monitoring site includes the following steps:

[0092] S21. Use positioning technology to deploy corresponding positioning equipment at each monitoring site to obtain the location information of each monitoring site. The location information of the monitoring site includes the longitude and latitude of the monitoring site.

[0093] S22. Randomly select a monitoring site from the monitoring sites as a benchmark monitoring site, and select a monitoring site adjacent to the benchmark monitoring site as a comparison monitoring site.

[0094] S23. Based on the location information of each monitoring site, the distance between the benchmark monitoring site and the comparison monitoring site is calculated using a geographic distance calculation formula.

[0095] Specifically, the formula for calculating geographic distance is:

[0096]

[0097] In the formula, D represents the distance between the benchmark monitoring site and the comparison monitoring site;

[0098] r represents the average radius of the Earth;

[0099] x1 represents the latitude of the benchmark monitoring site;

[0100] x2 represents the latitude of the comparison monitoring site;

[0101] y1 represents the longitude of the benchmark monitoring site;

[0102] y2 represents the longitude of the comparison monitoring site.

[0103] It should be noted that, in a specific embodiment, the first monitoring site is selected as the benchmark monitoring site, and a monitoring site adjacent to the benchmark monitoring site is obtained, which is recorded as the comparison monitoring site. The distance D1 between the benchmark monitoring site and the comparison monitoring site is calculated by the geographic distance calculation formula; the second monitoring site is selected as the benchmark monitoring site, and a monitoring site adjacent to the benchmark monitoring site is obtained, which is recorded as the comparison monitoring site. The distance D2 between the benchmark monitoring site and the comparison monitoring site is calculated by the geographic distance calculation formula, and so on, to obtain the distance Di between all benchmark monitoring points and comparison monitoring points in the marine environment monitoring area.

[0104] S3. Compare the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyze the changing trend of the environmental data, and determine the propagation speed of abnormal environmental data based on the analysis results.

[0105] Specifically, comparing the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyzing the change trend of the environmental data, and determining the propagation speed of the abnormal environmental data based on the analysis results includes the following steps:

[0106] S31. Extract historical standard environmental data of the benchmark monitoring site from the database.

[0107] It should be noted that historical standard environmental data refers to environmental data that has been recorded and stored in the database by benchmark monitoring sites over a period of time in the past, which has been verified and confirmed and represents normal or expected conditions; these data are usually used to compare with environmental data collected in real time to assess whether the current environmental conditions deviate from the normal or expected range.

[0108] S32. Calculate the difference between the historical standard environmental data of the benchmark monitoring site and the environmental data collected in real time, and make a preliminary judgment on whether there is abnormal environmental data based on the preset difference.

[0109] S33. Perform time series analysis on the real-time environmental data to analyze the changing trend of the data, and determine abnormal environmental data in combination with the preliminary abnormality judgment results.

[0110] S34. Based on the real-time environmental data of the comparison monitoring sites, a spatial distribution data set is established, and a spatial analysis algorithm is applied to extract the spatial distribution characteristics of the abnormal environmental data.

[0111] Specifically, the following steps are included to establish a spatial distribution data set based on the real-time environmental data of the comparison monitoring site and to apply the spatial analysis algorithm to extract the spatial distribution characteristics of the abnormal environmental data:

[0112] S341. Obtain environmental data of comparative monitoring sites, and use positioning technology to obtain location information of each comparative monitoring site.

[0113] S342. Combine the environmental data and location information of the comparison monitoring sites to establish a spatial distribution data set.

[0114] S343. Analyze the spatial distribution data set using a semivariance model, and perform interpolation within the spatial distribution data set to generate a spatial distribution map.

[0115] Specifically, the formula of the semivariance model is:

[0116]

[0117] Where T represents the estimated value of abnormal environmental data at latitude m and longitude n;

[0118] m represents the latitude of abnormal environmental data;

[0119] n represents the longitude of abnormal environmental data;

[0120] K represents the spatial distribution dataset;

[0121] k represents the real-time environmental data of the kth comparison monitoring site;

[0122] η represents the weight coefficient;

[0123] t represents time.

[0124] S344. Combine the abnormal environment data with the spatial distribution map to estimate the estimated value of the abnormal environment data.

[0125] S345. Based on the estimated value of the abnormal environment data, extract the spatial distribution characteristics of the abnormal environment data.

[0126] It should be noted that the spatial distribution characteristics of abnormal environmental data include the spatial location of the abnormal environmental data, the density and intensity of the abnormal environmental data, the spatial variation trend of the abnormal environmental data and the spatial distribution pattern of the abnormal environmental data.

[0127] For example, by using the semivariance model to analyze the spatial distribution data set and perform interpolation, a spatial distribution map that reflects the spatial distribution characteristics of abnormal environmental data can be generated. This map can intuitively display the distribution range, density, intensity and other information of the abnormal data; by combining the abnormal environmental data with the spatial distribution map, the estimated value of the abnormal environmental data can be estimated, and the spatial distribution characteristics of the abnormal phenomenon can be further quantified; based on the estimated value of the abnormal environmental data, more specific spatial distribution characteristics can be extracted, such as the cluster center, diffusion boundary, and impact range of the abnormal data, providing a basis for subsequent environmental monitoring and early warning.

[0128] S35. Based on the spatial distribution characteristics of the abnormal environmental data and the time series analysis results, the propagation speed of the abnormal environmental data in the marine environment is calculated.

[0129] It should be noted that the formula for propagation speed is:

[0130]

[0131] Where v represents the propagation speed of abnormal environmental data; d represents the distance between the reference monitoring site and the comparison monitoring site; △t represents the time difference.

[0132] S4. Combining distance and propagation speed, the linear propagation algorithm is used to calculate the arrival time of abnormal environmental data from the benchmark monitoring site to the comparison monitoring site.

[0133] Specifically, combining the distance and the propagation speed, the linear propagation algorithm is used to calculate the arrival time of the abnormal environmental data from the reference monitoring site to the comparison monitoring site, including the following steps:

[0134] S41. Based on the distance between the reference monitoring site and the corresponding comparison monitoring site and the propagation speed of the abnormal environmental data, a linear propagation algorithm is used to calculate the propagation time required for the abnormal environmental data to propagate from the reference monitoring site to the comparison monitoring site.

[0135] It should be noted that the formula of the linear propagation algorithm is:

[0136]

[0137] Where t represents the propagation time; d represents the distance between the reference monitoring site and the comparison monitoring site; and v represents the propagation speed of abnormal environmental data.

[0138] S42, obtaining the time when the abnormal environment data is at the reference monitoring site, integrating the propagation time, and calculating the arrival time when the abnormal environment data is propagated from the reference monitoring site to the comparison monitoring site.

[0139] It should be noted that arrival time = abnormal data occurrence time + propagation time t.

[0140] S5. Set the alarm start time according to the arrival time and issue the alarm information.

[0141] It should be noted that a reasonable alarm lead time (e.g. 30 minutes, 1 hour, etc.) is set according to the arrival time. This lead time can be determined according to the actual situation and the time required for emergency response. The alarm activation time is obtained by subtracting the preset alarm lead time from the estimated arrival time. For example, if the estimated arrival time is 14:00 and the preset alarm lead time is 1 hour, the alarm activation time is 13:00.

[0142] In addition, the alarm information includes the alarm level (such as low, medium, and high), the specific circumstances of the abnormal environmental data (such as current speed, wave height, etc.), the expected affected area, and recommended response measures; the alarm information is delivered via SMS, email, phone calls, mobile application push notifications, etc.

[0143] like Figure 2As shown, according to another embodiment of the present invention, there is also provided a marine environment monitoring and early warning system based on big data, the system comprising a data collection module 1, a position and distance calculation module 2, a propagation speed determination module 3, an arrival time calculation module 4 and an alarm issuing module 5;

[0144] Data collection module 1, used to deploy several monitoring stations in the marine environment monitoring area, collect environmental data in real time through sensors in the monitoring stations and transmit them to the database;

[0145] Position and distance calculation module 2, used to obtain the position information of each monitoring site by using positioning technology, and calculate the distance between the randomly selected reference monitoring site and the corresponding comparison monitoring site;

[0146] The propagation speed determination module 3 is used to compare the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyze the change trend of the environmental data, and determine the propagation speed of the abnormal environmental data based on the analysis results;

[0147] The arrival time calculation module 4 is used to calculate the arrival time of the abnormal environment data from the reference monitoring site to the comparison monitoring site by combining the distance and the propagation speed and using the linear propagation algorithm;

[0148] The alarm issuing module 5 is used to set the alarm start time according to the arrival time and issue the alarm information.

[0149] In summary, with the aid of the above technical solution of the present invention, by deploying monitoring sites and integrated sensor technology, real-time monitoring and data collection of the marine environment are achieved, which not only improves the immediacy and integrity of the data, but also utilizes data integration technology to integrate scattered data sources into a unified data set, thereby providing a comprehensive and accurate information basis for subsequent data analysis and early warning. By comparing the historical standard environmental data of the benchmark monitoring site with the real-time environmental data, the changing trend of the environmental data can be discovered in time and abnormal data can be identified, which helps to more accurately judge the current environmental state, thereby improving the sensitivity and reliability of the early warning system. By combining the distance between the monitoring sites and the propagation speed of the abnormal environmental data, the linear propagation algorithm is used to calculate the estimated arrival time of the abnormal data, which provides a scientific basis for setting the alarm activation time, can quickly identify and respond to potential environmental risks, and effectively shorten the early warning response time, thereby improving the efficiency and effectiveness of emergency response.

[0150] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A marine environment monitoring and early warning method based on big data, characterized in that: The method comprises the following steps: S1. Deploy several monitoring stations in the marine environment monitoring area, collect environmental data in real time through sensors in the monitoring stations and transmit them to the database; S2. Use positioning technology to obtain the location information of each monitoring site, and calculate the distance between the randomly selected benchmark monitoring site and the corresponding comparison monitoring site; S3. Compare the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyze the changing trend of the environmental data, and determine the propagation speed of abnormal environmental data based on the analysis results; S4, combining distance and propagation speed, using linear propagation algorithm to calculate the arrival time of abnormal environmental data from the reference monitoring site to the comparison monitoring site; S5. Set the alarm start time according to the arrival time and issue the alarm information.

2. The marine environment monitoring and early warning method based on big data according to claim 1 is characterized in that: The method of deploying a plurality of monitoring stations in the marine environment monitoring area, collecting environmental data in real time through sensors in the monitoring stations and transmitting the data to the database comprises the following steps: S11. Deploy several monitoring stations in the marine environment monitoring area according to the detection requirements, and configure corresponding sensors in each monitoring station; S12, using sensors to collect environmental data in real time and pre-process the environmental data; S13, fusing the pre-processed environmental data, and transmitting the fused environmental data to the database using wireless communication technology.

3. The marine environment monitoring and early warning method based on big data according to claim 2 is characterized in that: The method of fusing the pre-processed environmental data and transmitting the fused environmental data to the database using wireless communication technology includes the following steps: S131, extracting ocean environment parameters and ocean current information from the preprocessed environmental data; S132, synchronizing the time series of ocean environment parameters and ocean current information to obtain the ocean environment parameters and ocean current information corresponding to each time point; S133, using a Kalman filter algorithm to fuse the ocean environment parameters and ocean current information, wherein the ocean environment parameters and ocean current information are used as observation vectors, and through the prediction and update steps of the Kalman filter, the predicted state vector is gradually corrected to obtain fused environmental data; S134, packaging the integrated environmental data according to a preset format, and using wireless communication technology to transmit the packaged environmental data to a database.

4. The method for monitoring and early warning of marine environment based on big data according to claim 1 is characterized in that: The method of using positioning technology to obtain the location information of each monitoring site and calculating the distance between the randomly selected reference monitoring site and the corresponding comparison monitoring site includes the following steps: S21, using positioning technology to deploy corresponding positioning equipment at each monitoring site, and obtaining location information of each monitoring site, wherein the location information of each monitoring site includes the longitude and latitude of the monitoring site; S22. Randomly select a monitoring site from the monitoring sites as a benchmark monitoring site, and select a monitoring site adjacent to the benchmark monitoring site as a comparison monitoring site; S23. Based on the location information of each monitoring site, the distance between the benchmark monitoring site and the comparison monitoring site is calculated using a geographic distance calculation formula.

5. The method for monitoring and early warning of marine environment based on big data according to claim 4 is characterized in that: The geographic distance calculation formula is: In the formula, D represents the distance between the benchmark monitoring site and the comparison monitoring site; r represents the average radius of the Earth; x1 represents the latitude of the benchmark monitoring site; x2 represents the latitude of the comparison monitoring site; y1 represents the longitude of the benchmark monitoring site; y2 represents the longitude of the comparison monitoring site.

6. The marine environment monitoring and early warning method based on big data according to claim 1 is characterized in that: The step of comparing the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyzing the change trend of the environmental data, and determining the propagation speed of the abnormal environmental data based on the analysis result includes the following steps: S31, extracting historical standard environmental data of the benchmark monitoring site from the database; S32, calculating the difference between the historical standard environmental data of the benchmark monitoring site and the environmental data collected in real time, and making a preliminary judgment on whether there is abnormal environmental data based on the preset difference; S33, performing time series analysis on the real-time environmental data to analyze the change trend of the data, and determining abnormal environmental data in combination with the preliminary abnormality judgment result; S34, establishing a spatial distribution data set based on the real-time environmental data of the comparative monitoring site, and applying a spatial analysis algorithm to extract the spatial distribution characteristics of the abnormal environmental data; S35. Based on the spatial distribution characteristics of the abnormal environmental data and the time series analysis results, the propagation speed of the abnormal environmental data in the marine environment is calculated.

7. The method for monitoring and early warning of marine environment based on big data according to claim 6 is characterized in that: The method of establishing a spatial distribution data set based on the real-time environmental data of the comparison monitoring site and applying a spatial analysis algorithm to extract the spatial distribution characteristics of the abnormal environmental data includes the following steps: S341, obtaining environmental data of the comparative monitoring site, and using positioning technology to obtain location information of each comparative monitoring site; S342, combining the environmental data and location information of the comparison monitoring site to establish a spatial distribution data set; S343, analyzing the spatial distribution data set using a semivariance model, and interpolating within the spatial distribution data set to generate a spatial distribution map; S344, combining the abnormal environment data with the spatial distribution map, estimating an estimated value of the abnormal environment data; S345. Based on the estimated value of the abnormal environment data, extract the spatial distribution characteristics of the abnormal environment data.

8. The marine environment monitoring and early warning method based on big data according to claim 7 is characterized in that: The formula for the semivariance model is: Where T represents the estimated value of abnormal environmental data at latitude m and longitude n; m represents the latitude of abnormal environmental data; n represents the longitude of abnormal environmental data; K represents the spatial distribution dataset; k represents the real-time environmental data of the kth comparison monitoring site; η represents the weight coefficient; t represents time.

9. The marine environment monitoring and early warning method based on big data according to claim 1 is characterized in that: The method of combining distance and propagation speed and using a linear propagation algorithm to calculate the arrival time of abnormal environmental data from the reference monitoring site to the comparison monitoring site includes the following steps: S41, combining the distance between the reference monitoring site and the corresponding comparison monitoring site and the propagation speed of the abnormal environment data, using a linear propagation algorithm, calculating the propagation time required for the abnormal environment data to propagate from the reference monitoring site to the comparison monitoring site; S42, obtaining the time when the abnormal environment data is at the reference monitoring site, integrating the propagation time, and calculating the arrival time when the abnormal environment data is propagated from the reference monitoring site to the comparison monitoring site.

10. A marine environment monitoring and early warning system based on big data, used to implement the marine environment monitoring and early warning method based on big data described in any one of claims 1 to 9, characterized in that: The system includes a data collection module, a position and distance calculation module, a propagation speed determination module, an arrival time calculation module and an alarm issuance module; The data collection module is used to deploy a number of monitoring stations in the marine environment monitoring area, collect environmental data in real time through sensors in the monitoring stations and transmit them to the database; The position and distance calculation module is used to obtain the position information of each monitoring site by using positioning technology, and calculate the distance between the randomly selected reference monitoring site and the corresponding comparison monitoring site; The propagation speed determination module is used to compare the historical standard environmental data of the benchmark monitoring site with the environmental data collected in real time, analyze the change trend of the environmental data, and determine the propagation speed of the abnormal environmental data based on the analysis results; The arrival time calculation module is used to combine the distance and the propagation speed and use the linear propagation algorithm to calculate the arrival time of the abnormal environment data from the reference monitoring site to the comparison monitoring site; The alarm publishing module is used to set the alarm start time according to the arrival time and publish the alarm information.

Images