Data applicability assessment method and system for early warning of ocean hydrodynamic disasters

Abstract

The invention relates to the technical field of data evaluation, in particular to a data applicability evaluation method and system for early warning of ocean hydrodynamic disasters, and the method comprises the steps: carrying out the change feature extraction of data in different time periods during the data applicability evaluation of the early warning of the ocean hydrodynamic disasters; according to the method, the change characteristics of the data of different time scales can be extracted, and during data applicability evaluation, applicability evaluation is performed on the change characteristics of different time periods instead of directly adopting multi-source data, so that the data volume participating in applicability evaluation is greatly reduced, and the efficiency of data evaluation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data evaluation, and in particular to a data applicability evaluation method and system for early warning of marine hydrodynamic disasters. Background Art

[0002] The basis of marine hydrodynamic early warning is built on the long-term and real-time monitoring of the marine dynamic environment. At present, a three-dimensional marine monitoring system based on remote sensing, ocean stations, offshore buoys, drones and other means has been built. These monitoring methods can realize three-dimensional real-time monitoring of the marine dynamic disaster process before, during and after the disaster, and provide data support for early warning; with the development of big data and artificial intelligence technology, the marine hydrodynamic early warning system is gradually developing in the direction of intelligence and automation. Among them, the development of intelligence and automation is inseparable from the operation of monitoring data. However, the applicability of data is of great significance to the early warning of marine hydrodynamic disasters.

[0003] There are technical solutions for evaluating data suitability in the prior art. For example, a data suitability evaluation method is mentioned in the journal article "Analysis and Evaluation of Suitability of Multivariate Fusion Real-time Temperature Data", which uses correlation analysis and error analysis to test and evaluate the accuracy and applicability of the 2020 winter grid actual 2 m temperature in Weixian area; however, the above-mentioned scheme using correlation analysis and error analysis to evaluate data suitability has the problem that the evaluation method is simple and the evaluation results are not accurate. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a data applicability assessment method for marine hydrodynamic disaster warning, which is used to solve the problems existing in the prior art.

[0005] The present invention provides a data applicability assessment method for marine hydrodynamic disaster warning, comprising the following steps: S1: Acquire multi-source data for early warning of marine hydrodynamic hazards; S2: performing data preprocessing operations on the multi-source data; S3: performing a change feature extraction operation of different time periods on the multi-source data pre-processed by S2; S4: Acquire measured data of the multi-source data; S5: performing a change feature extraction operation on the measured data at different time periods; S6: Evaluate the applicability of the variation characteristics of the measured data and the variation characteristics of the multi-source data.

[0006] Preferably, the multi-source data used for marine hydrodynamic disaster warning includes: marine hydrological and meteorological data, marine wave data, and meteorological data.

[0007] Preferably, the multi-source data are reanalysis data based on different sources.

[0008] Preferably, the marine hydrological and meteorological data include ocean temperature data, ocean salinity data, ocean current speed data, ocean current direction data, sea level height data, wind speed data, wind direction data, and tide level data; The wave data includes significant wave height data, main wave period data, main wave direction data, and wave spectrum; The meteorological data includes temperature data, air pressure data, humidity data, rainfall data and atmospheric circulation data.

[0009] Preferably, the data preprocessing operations include missing value processing, outlier value processing, duplicate value processing, and data standardization.

[0010] Preferably, the missing value processing is to use one of the mean, median and mode to fill in the data; The outlier processing is to identify outliers through a box plot, and then delete the identified outliers; The duplicate value processing is to detect and delete duplicate records to ensure the uniqueness of the data set; The data normalization is to integrate the multi-source data into the interval (0, 1) by using the maximum and minimum normalization method.

[0011] Preferably, in S3, the different time periods include: yearly period, monthly period and weekly period.

[0012] Preferably, the annual cycle change feature extraction operation for the data pre-processed in S2 is specifically: taking the change rate between the current year's data and the previous year's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data as the change feature; Preferably, the annual cycle change feature extraction operation for the data pre-processed in S2 is specifically: taking the change rate between the current year's data and the previous year's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data as the change feature; The operation of extracting the monthly change features of the data pre-processed by S2 is specifically as follows: taking the change rate of the current month's data and the previous month's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data as the change feature; The specific operation of extracting the weekly change features of the data pre-processed by S2 is as follows: the change rate of the current week's data and the previous week's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data is used as the change feature.

[0013] According to another aspect of the present invention, a data suitability assessment system for marine hydrodynamic disaster early warning is provided, wherein the system adopts the above-mentioned data suitability assessment method for marine hydrodynamic disaster early warning, and the system comprises: Multi-source data acquisition module, which acquires multi-source data for early warning of marine hydrodynamic disasters; A preprocessing module, used for performing data preprocessing operations on the multi-source data; A change feature extraction module, used for performing change feature extraction operations of different time periods on the data preprocessed by the preprocessing module and the measured data; A measured data acquisition module, used to acquire the measured data of the multi-source data; The applicability evaluation module is used to evaluate the applicability of the change characteristics of the measured data and the change characteristics of the multi-source data.

[0014] The embodiments of the present invention have the following technical effects: When evaluating the suitability of data for marine hydrodynamic disaster warning, the present invention performs a change feature extraction operation on the data at different time periods, and can extract the change features of the data at different time scales. When evaluating the suitability of the data, the change features of the different time periods are evaluated for suitability, rather than directly using multi-source data for the applicability evaluation. This greatly reduces the amount of data involved in the applicability evaluation and improves the efficiency of the data evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of a method for evaluating data applicability for marine hydrodynamic disaster warning provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0018] Attached Figure 1A flow chart of a method for evaluating the suitability of data for marine hydrodynamic disaster warning is shown in the attached figure. Figure 1 As shown, a data applicability assessment method for marine hydrodynamic disaster warning includes the following steps: S1: Acquire multi-source data for early warning of marine hydrodynamic hazards; Among them, marine hydrodynamic disaster warning requires multiple types of data, that is, multi-source data. In this embodiment, the multi-source data used for marine hydrodynamic disaster warning includes: marine hydrological and meteorological data, marine wave data, and meteorological data; the multi-source data is reanalysis data based on different sources; Among them, the ocean hydrological and meteorological data include ocean temperature data, ocean salinity data, ocean current speed data, ocean current direction data, sea level height data, wind speed data, wind direction data, and tide level data; the ocean temperature and ocean salinity are used to monitor the thermal structure and salinity changes of seawater, and these parameters have a direct impact on ocean circulation and density changes; the ocean current speed and ocean current direction data are obtained through buoys, ship measurements, and satellite remote sensing, and are used to analyze ocean circulation patterns and their changes; the sea level height data is used to monitor the trend of sea level rise and short-term fluctuations, and is the key data for storm surge and tsunami warnings; the wind speed data and wind direction data are the wind fields on the ocean surface, which are important factors in causing disasters such as waves and storm surges; the tide level data is used to monitor tidal changes through equipment such as wave and tide gauges, and is used for storm surge warnings; The wave data includes significant wave height data, main wave period data, main wave direction data, and wave spectrum; wherein the significant wave height data, main wave period data, and main wave direction data are used to assess the intensity and propagation direction of ocean waves, and are the core data for marine disaster warning; the wave spectrum information is used to analyze the frequency and energy distribution of waves, and help predict extreme marine disaster events; The meteorological data includes temperature data, air pressure data, humidity data, rainfall data and atmospheric circulation data; the temperature data, air pressure data, humidity data and rainfall data are closely related to the occurrence of marine disasters, for example, changes in air pressure may trigger storm surges; the atmospheric circulation data is obtained through meteorological satellites and numerical weather forecast models, and is used to predict the generation and development of marine disasters.

[0019] S2: performing data preprocessing operations on the multi-source data; Multi-source data preprocessing is an important part of data analysis, and its purpose is to organize data from different sources into a form suitable for analysis.

[0020] The data preprocessing operations include missing value processing, outlier value processing, duplicate value processing, and data standardization; Wherein, the missing value processing is to use one of the mean, median, mode, etc. to fill in the data; The outlier processing is to identify outliers through a box plot, and then delete the identified outliers; The duplicate value processing is to detect and delete duplicate records to ensure the uniqueness of the data set; The data standardization is to integrate the multi-source data into the interval (0, 1) by using the maximum and minimum normalization method; Through the above operations, multi-source data can be organized into a high-quality form suitable for analysis, thereby improving the accuracy and efficiency of data suitability assessment.

[0021] S3: performing a change feature extraction operation at different time periods on the data pre-processed by S2; In this step, the different time periods include: yearly cycle, monthly cycle, weekly cycle; The specific operation of extracting the annual cycle variation characteristics of the data pre-processed by S2 is as follows: the variation rate between the current year's data and the previous year's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data is used as the variation characteristic; The specific operation of extracting the monthly change features of the data pre-processed by S2 is as follows: taking the change rate of the current month's data and the previous month's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data as the change feature; The specific operation of extracting the weekly change features of the data pre-processed by S2 is as follows: taking the change rate of the current week's data and the previous week's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data as the change feature; Through this step, the change characteristics of data at different time scales can be extracted. When evaluating the suitability of data, the change characteristics of the different time periods are evaluated for suitability, rather than directly using multi-source data for suitability evaluation. This greatly reduces the amount of data involved in the suitability evaluation and improves the efficiency of data evaluation.

[0022] S4: Acquire measured data of the multi-source data; In this embodiment, the measured data of the multi-source data is the data actually monitored by each monitoring station; In the process of evaluating data adaptability, the measured data is used as the true value.

[0023] S5: performing a change feature extraction operation on the measured data at different time periods; The change feature extraction cycle of the measured data also includes: annual cycle, monthly cycle, weekly cycle; and the change feature extraction operation of different time periods of the measured data is the same as the method in S3.

[0024] S6: Evaluate the applicability of the variation characteristics of the measured data and the variation characteristics of the multi-source data; In this step, the mean error, dispersion index, and root mean square error are used as suitability evaluation indicators to obtain the data quality of reanalysis data of different periods.

[0025] Embodiment 2, the present invention further provides a data suitability assessment system for marine hydrodynamic disaster warning, the system adopts a data suitability assessment method for marine hydrodynamic disaster warning in embodiment 1, and the system comprises: Multi-source data acquisition module, which acquires multi-source data for early warning of marine hydrodynamic disasters; A preprocessing module, used for performing data preprocessing operations on the multi-source data; A change feature extraction module, used for performing change feature extraction operations of different time periods on the data preprocessed by the preprocessing module and the measured data; A measured data acquisition module, used to acquire the measured data of the multi-source data; The applicability evaluation module is used to evaluate the applicability of the change characteristics of the measured data and the change characteristics of the multi-source data.

[0026] Embodiment 3, the present invention also provides an electronic device, including one or more processors and a memory.

[0027] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0028] The memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may run the program instructions to implement a data applicability assessment method for marine hydrodynamic disaster warning and / or other desired functions of any embodiment of the present application described above. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0029] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown). The input device may include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including early warning information, braking force, etc. The output device may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0030] Of course, for the sake of simplicity, components such as buses, input / output interfaces, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application conditions.

[0031] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to implement the functions of a data suitability assessment method for marine hydrodynamic disaster warning provided by any embodiment of the present application.

[0032] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0033] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor implements a data suitability assessment method for marine hydrodynamic disaster warning provided by any embodiment of the present application.

[0034] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0035] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A data applicability assessment method for marine hydrodynamic disaster warning, characterized in that: The following steps are involved: S1: Acquire multi-source data for early warning of marine hydrodynamic hazards; S2: performing data preprocessing operations on the multi-source data; S3: performing a change feature extraction operation of different time periods on the multi-source data pre-processed by S2; S4: Acquire measured data of the multi-source data; S5: performing a change feature extraction operation on the measured data at different time periods; S6: Evaluate the applicability of the variation characteristics of the measured data and the variation characteristics of the multi-source data.

2. The data applicability assessment method for marine hydrodynamic disaster warning according to claim 1 is characterized by: In S1, the multi-source data used for early warning of marine hydrodynamic disasters include: marine hydrological and meteorological data, marine wave data, and meteorological data.

3. The data applicability assessment method for marine hydrodynamic disaster warning according to claim 2 is characterized by: The multi-source data are reanalysis data based on different sources.

4. The data applicability assessment method for marine hydrodynamic disaster warning according to claim 2 is characterized by: The marine hydrological and meteorological data include ocean temperature data, ocean salinity data, ocean current speed data, ocean current direction data, sea level height data, wind speed data, wind direction data, and tide level data; The wave data includes significant wave height data, main wave period data, main wave direction data, and wave spectrum; The meteorological data includes temperature data, air pressure data, humidity data, rainfall data and atmospheric circulation data.

5. The data applicability assessment method for marine hydrodynamic disaster early warning according to claim 1 is characterized by: The data preprocessing operations include missing value processing, outlier value processing, duplicate value processing, and data standardization.

6. The data applicability assessment method for marine hydrodynamic disaster warning according to claim 5 is characterized by: The missing value processing is to use one of the mean, median and mode to fill in the data; The outlier processing is to identify outliers through a box plot, and then delete the identified outliers; The duplicate value processing is to detect and delete duplicate records to ensure the uniqueness of the data set; The data normalization is to integrate the multi-source data into the interval (0, 1) by using the maximum and minimum normalization method.

7. The data applicability assessment method for marine hydrodynamic disaster warning according to claim 1 is characterized by: In S3, the different time periods include: yearly period, monthly period, and weekly period.

8. The data applicability assessment method for marine hydrodynamic disaster early warning according to claim 2 is characterized by: The specific operation of extracting the annual cycle change characteristics of the data pre-processed by S2 is: taking the change rate of the current year's data and the previous year's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data as the change characteristics.

9. The method for evaluating the suitability of data for early warning of marine hydrodynamic disasters according to claim 8, characterized in that: The operation of extracting the monthly change features of the data pre-processed by S2 is specifically as follows: taking the change rate of the current month's data and the previous month's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data as the change feature; The specific operation of extracting weekly change features of the data pre-processed by S2 is as follows: the change rate of the current week's data and the previous week's data of the ocean hydrological and meteorological data, ocean wave data, and meteorological data is used as a change feature.

10. A data suitability assessment system for marine hydrodynamic disaster warning, characterized in that: The system adopts a data applicability assessment method for marine hydrodynamic disaster warning according to any one of claims 1 to 9, and the system comprises: Multi-source data acquisition module, which acquires multi-source data for early warning of marine hydrodynamic disasters; A preprocessing module, used for performing data preprocessing operations on the multi-source data; A change feature extraction module, used to perform change feature extraction operations of different time periods on the data preprocessed by the preprocessing module and the measured data; A measured data acquisition module, used to acquire the measured data of the multi-source data; The applicability evaluation module is used to evaluate the applicability of the change characteristics of the measured data and the change characteristics of the multi-source data.

Images