Marine disaster risk assessment method based on multi-parameter observation

Abstract

The invention relates to the field of multi-parameter observation disaster early warning, and discloses a marine disaster risk assessment method based on multi-parameter observation, which is used for solving the problems that a fixed sampling frequency cannot respond to emergencies in time, and a traditional method is difficult to update a disaster assessment result in time once meteorological sudden change or marine environment abnormity occurs. The method comprises the following steps of: processing and analyzing data, calculating to obtain a marine environment anomaly index, a meteorological anomaly index, a geological environment anomaly index and a sea level anomaly index, further calculating a comprehensive disaster risk coefficient, and comparing the comprehensive disaster risk coefficient with a historical disaster early warning threshold value to obtain a disaster early warning result. And judging whether the ocean data acquisition frequency needs to be adjusted or not, and predicting an environment change trend in a period of time in the future by combining with a machine learning model. The method has efficient disaster early warning and response capabilities, can improve the data acquisition efficiency to the maximum extent, optimizes the system performance, and reduces the resource waste.

Description

Technical Field

[0001] This invention relates to the field of multi-parameter observation disaster early warning, and more specifically to a method for marine disaster risk assessment based on multi-parameter observation. Background Technology

[0002] Marine disaster assessment technology is used to predict and assess the probability, intensity, and impact range of various marine disaster events (such as typhoons, storms, and tsunamis). Traditional marine disaster assessment methods mainly rely on meteorological data, marine environmental monitoring data, and records of historical disaster events. They predict the occurrence of disasters by establishing mathematical models or machine learning algorithms. These assessment methods typically use historical data and data at fixed time points to extrapolate potential disaster risks and are widely used in fields such as disaster early warning, emergency management, and infrastructure construction.

[0003] In existing technologies, most marine disaster assessment systems conduct risk assessments within specific time periods, relying on timed data collection, such as daily or hourly sampling, or regular monitoring based on disaster type. They predict disaster risks based on historical data and regularly collected environmental data. Although these systems can provide relatively accurate long-term disaster prediction results, they lack real-time updates and dynamic response capabilities. This means that once environmental changes or sudden disaster signs occur, existing systems are usually unable to respond in a timely manner, thus affecting the effectiveness of disaster early warning and the efficiency of emergency response.

[0004] Based on existing technologies and with the development of monitoring technology, how to adjust the sampling frequency in real time according to the situation and collect more representative data has become an urgent problem to be solved. By intelligently adjusting the sampling frequency, the system can avoid over-collecting unnecessary data, thereby saving storage, computing and energy consumption.

[0005] However, the above-mentioned technologies have at least the following technical problems:

[0006] Most existing marine disaster assessment systems conduct risk assessments within specific time periods, relying on timed data collection. The fixed sampling frequency cannot respond promptly to emergencies. Once a sudden change in weather or an abnormal marine environment occurs, traditional methods cannot update disaster assessment results in a timely manner, leading to delays in disaster warnings and emergency responses. Summary of the Invention

[0007] In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides a marine disaster risk assessment method based on multi-parameter observation to solve the problems existing in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A method for marine disaster risk assessment based on multi-parameter observation includes the following steps: Step 1, acquiring marine environmental data, meteorological data, geological data, and sea level data through marine buoys, remote sensing satellites, earthquake and tsunami monitoring networks, and national meteorological platforms; Step 2, calculating marine environmental anomaly indices, meteorological anomaly indices, geological environmental anomaly indices, and sea level anomaly indices using marine environmental data, meteorological data, geological environmental data, and sea level height data, and calculating a comprehensive disaster risk coefficient based on these indices, and determining whether to adjust the marine data acquisition frequency based on the comprehensive disaster risk coefficient; Step 3, if it is determined that the marine data acquisition frequency needs to be adjusted, adjusting the default acquisition frequency to obtain the current acquisition frequency; Step 4, monitoring marine environmental data using the current acquisition frequency, predicting environmental change trends over a future period using machine learning models, and conducting a marine disaster risk assessment based on these environmental change trends.

[0010] Preferably, the steps for obtaining the comprehensive disaster risk coefficient are as follows: First, acquire marine environmental data, including seawater temperature, ocean current velocity, sea surface pressure, and seawater density; then, assess the marine environmental anomaly index using these data. Second, acquire meteorological data, including wind speed, precipitation, cloud cover, and radiation; then, assess the meteorological anomaly index using these data. Third, acquire geological environmental data, including geological structure, soil and rock properties, topography, and groundwater; then, assess the geological environmental anomaly index using these data. Fourth, acquire sea level data, including ocean thermal expansion, groundwater volume, climate change data, and ocean circulation; then, assess the sea level anomaly index using these data. Finally, normalize the marine environmental anomaly index, meteorological anomaly index, geological environmental anomaly index, and sea level anomaly index; and finally, calculate the comprehensive disaster risk coefficient using the normalized marine environmental anomaly index, meteorological anomaly index, geological environmental anomaly index, and sea level anomaly index.

[0011] Preferably, the steps for obtaining the marine environment anomaly index are as follows: First, obtain the seawater temperature from the marine environment data; calculate the difference between the seawater temperature in the marine data and the historical average temperature, and then calculate the ratio of this difference to the historical average temperature to obtain a seawater temperature anomaly coefficient. Second, obtain the ocean current velocity from the marine data; calculate the difference between the ocean current velocity in the marine data and the historical average ocean current velocity, and then calculate the ratio of this difference to the historical average ocean current velocity to obtain an ocean current velocity anomaly coefficient. Third, obtain the sea surface pressure from the marine data; calculate the difference between the sea surface pressure in the marine data and the historical average sea surface pressure, and then calculate the ratio of this difference to the historical average sea surface pressure to obtain a sea surface pressure anomaly coefficient. Fourth, obtain the seawater density from the marine data; calculate the difference between the seawater density in the marine data and the historical average seawater density, and then calculate the ratio of this difference to the historical average seawater density to obtain a seawater density anomaly coefficient. Finally, normalize the seawater temperature anomaly coefficient, ocean current velocity anomaly coefficient, sea surface pressure anomaly coefficient, and seawater density anomaly coefficient, and then calculate the normalized seawater temperature anomaly coefficient, ocean current velocity anomaly coefficient, sea surface pressure anomaly coefficient, and seawater density anomaly coefficient to obtain the marine environment anomaly index.

[0012] Preferably, the steps for obtaining the meteorological anomaly index are as follows: Obtaining wind speed from meteorological data, calculating the difference between the wind speed in the meteorological data and historical wind speed, and then calculating the ratio of the difference to the historical wind speed to obtain a wind speed anomaly coefficient; obtaining precipitation from meteorological data, calculating the difference between the precipitation in the meteorological data and historical average precipitation, and then calculating the ratio of the difference to the historical average precipitation to obtain a precipitation anomaly coefficient; obtaining cloud cover from meteorological data, calculating the difference between the cloud cover in the meteorological data and sunshine duration, and then calculating the ratio to the sunshine duration to obtain a cloud cover anomaly coefficient; obtaining radiation from meteorological data, interpolating the radiation in the meteorological data and standard radiation value, and then calculating the ratio to the standard radiation value to obtain a radiation value anomaly coefficient; normalizing the wind speed anomaly coefficient, precipitation anomaly coefficient, cloud cover anomaly coefficient, and radiation value anomaly coefficient, and then calculating the normalized wind speed anomaly coefficient, precipitation anomaly coefficient, cloud cover anomaly coefficient, and radiation value anomaly coefficient to obtain a meteorological anomaly index.

[0013] Preferably, the steps for obtaining the geological environment anomaly index are as follows: First, obtain the geological structure from the geological environment data; calculate the difference between the geological structure in the geological environment and the geological stability of the historical disaster-occurring area, and then calculate the ratio between the difference and the geological stability of the historical disaster-occurring area to obtain the geological structure anomaly coefficient; second, obtain the soil and rock properties from the geological environment data; calculate the difference between the soil and rock properties in the geological environment and the standard soil and rock strength, and then calculate the ratio between the difference and the standard soil and rock strength to obtain the soil and rock property anomaly coefficient; third, obtain the topography and geomorphology from the geological environment data; calculate the difference between the topography and geomorphology in the geological environment and the typical topography risk factor, and then calculate the ratio between the difference and the typical topography risk factor to obtain the topography and geomorphology anomaly coefficient; fourth, obtain the groundwater from the geological environment data; calculate the difference between the groundwater in the geological environment and the standard groundwater level, and then calculate the ratio between the difference and the standard groundwater level to obtain the groundwater anomaly coefficient; fifth, normalize the geological structure anomaly coefficient, soil and rock property anomaly coefficient, topography and geomorphology anomaly coefficient, and groundwater anomaly coefficient, and then calculate the normalized geological structure anomaly coefficient, soil and rock property anomaly coefficient, topography and geomorphology anomaly coefficient, and groundwater anomaly coefficient to obtain the geological environment anomaly index.

[0014] Preferably, the steps for obtaining the sea level anomaly index are as follows: First, obtain the ocean thermal expansion from the sea level data; calculate the difference between the ocean thermal expansion and seawater temperature change in the sea level data, and then calculate the ratio of the difference to the seawater temperature change to obtain the ocean thermal expansion coefficient. Second, obtain the soil and rock properties from the sea level data; calculate the difference between the groundwater volume and soil permeability from the sea level data, and then calculate the ratio of the difference to the soil permeability to obtain the groundwater influence coefficient. Third, obtain the topography from the sea level data; calculate the difference between the climate change data and historical climate data anomalies from the sea level data, and then calculate the ratio of the difference to the historical climate data anomalies to obtain the climate change influence coefficient. Fourth, obtain the groundwater from the sea level data; calculate the difference between the ocean circulation and seawater density change from the sea level data, and then calculate the ratio of the difference to the seawater density change to obtain the ocean circulation influence coefficient. Fifth, normalize the ocean thermal expansion coefficient, groundwater influence coefficient, climate change influence coefficient, and ocean circulation influence coefficient; and then calculate the sea level anomaly index using the normalized ocean thermal expansion coefficient, groundwater influence coefficient, climate change influence coefficient, and ocean circulation influence coefficient.

[0015] Preferably, the specific steps for determining whether to adjust the marine data collection frequency based on the comprehensive disaster risk coefficient are as follows: compare the comprehensive disaster risk coefficient with the historical disaster warning threshold; when the comprehensive disaster risk coefficient is greater than or equal to the historical disaster warning threshold, it is determined that there is a disaster in the marine environment, and the marine data collection frequency is adjusted; when the comprehensive disaster risk coefficient is less than the historical disaster warning threshold, timed data collection continues.

[0016] Preferably, the step of adjusting the default collection frequency is as follows: when the comprehensive disaster risk coefficient is less than the historical disaster early warning threshold, the marine environment is defined as low risk, and the marine data collection frequency is reduced to obtain the current collection frequency. The specific steps for obtaining this frequency are as follows: In the formula, This is the current sampling frequency; the default sampling frequency is also mentioned. Adjust the sampling frequency increment for low-risk conditions; When the comprehensive disaster risk coefficient is greater than or equal to the historical disaster risk threshold, the marine environment is defined as high-risk. The frequency of marine data collection is increased to obtain the current collection frequency. The specific steps for obtaining this frequency are as follows: In the formula, This is the current sampling frequency. This is the default sampling frequency. Adjust the sampling frequency increment for high-risk conditions.

[0017] The technical effects and advantages of this invention are as follows:

[0018] By processing and analyzing the data, marine environmental anomaly indices, meteorological anomaly indices, geological environmental anomaly indices, and sea-level anomaly indices are calculated. A comprehensive disaster risk coefficient is then calculated. Based on a comparison of the comprehensive disaster risk coefficient with historical disaster warning thresholds, it is determined whether the frequency of marine data collection needs to be adjusted. Furthermore, a machine learning model is used to predict environmental change trends over a future period. This method possesses highly efficient disaster warning and response capabilities, maximizing data collection efficiency, optimizing system performance, and reducing resource waste. Attached Figure Description

[0019] Figure 1 A flowchart illustrating a method for intelligent temperature control based on multi-source environmental perception, provided in this application embodiment. Detailed Implementation

[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The marine disaster risk assessment method based on multi-parameter observation involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] This invention provides a method for marine disaster risk assessment based on multi-parameter observations, such as... Figure 1 As shown, it includes the following steps:

[0022] Step one involves acquiring marine environmental data, meteorological data, geological data, and sea level data through ocean buoys, remote sensing satellites, earthquake and tsunami monitoring networks, and the national meteorological platform.

[0023] Step two involves calculating the marine environment anomaly index, meteorological anomaly index, geological environment anomaly index, and sea level anomaly index using marine environmental data, meteorological data, geological environmental data, and sea level height data. The comprehensive disaster risk coefficient is then calculated based on these indices. Finally, the decision is made on whether to adjust the marine data collection frequency based on the comprehensive disaster risk coefficient.

[0024] In this embodiment, it should be noted that the specific steps for obtaining the comprehensive disaster risk coefficient are as follows:

[0025] Marine environmental data is acquired, including seawater temperature, ocean current speed, sea surface pressure, and seawater density. Marine environmental anomaly indices are obtained by assessing seawater temperature, ocean current speed, sea surface pressure, and seawater density.

[0026] Meteorological data is acquired, including wind speed, precipitation, cloud cover, and radiation. Meteorological anomaly indices are obtained by assessing wind speed, precipitation, cloud cover, and radiation.

[0027] Geological environment data is obtained, including geological structure, soil and rock properties, topography and geomorphology, and groundwater. Geological environment anomaly index is obtained by assessing geological structure, soil and rock properties, topography and geomorphology, and groundwater.

[0028] Sea level data is acquired, including data on ocean thermal expansion, groundwater volume, climate change, and ocean circulation. The sea level anomaly index is obtained by assessing ocean thermal expansion, groundwater volume, climate change, and ocean circulation.

[0029] The marine environmental anomaly index, meteorological anomaly index, geological environmental anomaly index, and sea level anomaly index are normalized. The comprehensive disaster risk coefficient is then calculated from these normalized indices. The specific steps are as follows:

[0030] ;

[0031] In the formula, To determine the comprehensive disaster risk coefficient, This is a marine environmental anomaly index. This is a meteorological anomaly index. This is a geological environment anomaly index. The sea level anomaly index is calculated using a multiplication and root formula, which can effectively balance the impact of various factors on the comprehensive disaster risk coefficient. This avoids excessive deviations in the results when a single anomaly index is too high or too low. By calculating the fourth root, the impact of extreme values ​​can be reduced to a certain extent, making the final risk assessment more stable and balanced, while maintaining the relative importance of each factor without the need to introduce a complex weighting mechanism.

[0032] In this embodiment, it should be noted that the specific steps for obtaining the marine environmental anomaly index are as follows:

[0033] The seawater temperature is obtained from the marine environmental data. The difference between the seawater temperature in the marine data and the historical average temperature is calculated, and the ratio of the difference to the historical average temperature is calculated to obtain the seawater temperature anomaly coefficient.

[0034] The ocean current velocity is obtained from the ocean data. The difference between the ocean current velocity in the ocean data and the historical average ocean current velocity is calculated, and the ratio of the difference to the historical average ocean current velocity is calculated to obtain the ocean current velocity anomaly coefficient.

[0035] The sea surface pressure is obtained from the ocean data. The difference between the sea surface pressure in the ocean data and the historical average sea surface pressure is calculated, and the ratio of the difference to the historical average sea surface pressure is calculated to obtain the sea surface pressure anomaly coefficient.

[0036] The seawater density is obtained from the ocean data. The difference between the seawater density in the ocean data and the historical average seawater density is calculated, and the ratio of the difference to the historical average seawater density is calculated to obtain the seawater density anomaly coefficient.

[0037] The anomaly coefficients of seawater temperature, ocean current velocity, sea surface pressure, and seawater density are normalized. The normalized seawater temperature, ocean current velocity, sea surface pressure, and seawater density anomaly coefficients are then used to calculate the marine environmental anomaly index. The specific steps are as follows:

[0038] ;

[0039] In the formula, This is a marine environmental anomaly index. This is the seawater temperature anomaly coefficient. This is the ocean current velocity anomaly coefficient. This is the sea surface pressure anomaly coefficient. The seawater density anomaly coefficient is standardized using a logarithmic product formula. By taking the logarithm of each anomaly coefficient, the excessive influence of extreme values ​​on the final result can be effectively reduced. The logarithmic property compresses larger outliers, thus avoiding extreme distortion of the comprehensive index when an outlier deviates too much from the normal range.

[0040] In this embodiment, it should be noted that the specific steps for obtaining the meteorological anomaly index are as follows:

[0041] The wind speed is obtained from the meteorological data. The wind speed in the meteorological data is calculated by comparing the difference between the wind speed in the meteorological data and the historical wind speed, and then the ratio of the difference to the historical wind speed is calculated to obtain the wind speed anomaly coefficient.

[0042] The precipitation data is obtained from meteorological data. The difference between the precipitation data and the historical average precipitation is calculated, and then the ratio of the difference to the historical average precipitation is calculated to obtain the precipitation anomaly coefficient.

[0043] Obtain cloud cover from meteorological data, calculate the difference between cloud cover and sunshine duration, and then calculate the ratio of the difference to sunshine duration to obtain the cloud cover anomaly coefficient.

[0044] The radiation in the meteorological data is obtained, and the ratio of the radiation in the meteorological data to the standard radiation value is calculated to obtain the radiation value anomaly coefficient.

[0045] The anomaly coefficients of wind speed, rainfall, cloud cover, and radiation are normalized. The meteorological anomaly index is then calculated from these normalized coefficients. The specific steps are as follows:

[0046] ;

[0047] In the formula, This is a meteorological anomaly index. This is the wind speed anomaly coefficient. This represents the rainfall anomaly coefficient. This represents the cloud cover anomaly coefficient. The radiation anomaly coefficient is calculated using the formula of the fourth power square root. This method avoids the excessive influence of a single factor on the final result and balances the contribution of various factors to the meteorological anomaly index. If a coefficient value is very high or very low, the square root method can reduce its amplification effect on the index.

[0048] In this embodiment, it should be noted that the specific steps for obtaining the geological environment anomaly index are as follows:

[0049] The geological structure is obtained from the geological environment data. The difference between the geological structure in the geological environment and the geological stability of the historical disaster area is calculated, and the ratio of the difference between the geological structure and the geological stability of the historical disaster area is calculated to obtain the geological structure anomaly coefficient.

[0050] The rock and soil properties in the geological environment data are obtained. The difference between the rock and soil properties in the geological environment and the standard rock and soil strength is calculated, and the ratio of the difference to the standard rock and soil strength is calculated to obtain the rock and soil property anomaly coefficient.

[0051] The topography and geomorphology in the geological environment data are obtained. The difference between the topography and geomorphology in the geological environment and the typical topographic risk factor is calculated, and the ratio of the difference with the typical topographic risk factor is calculated to obtain the topographic and geomorphological anomaly coefficient.

[0052] The process involves acquiring groundwater data from geological environments, calculating the difference between the groundwater level and the standard groundwater level, and then calculating the ratio between the groundwater level and the standard groundwater level to obtain the groundwater anomaly coefficient. The geological structure anomaly coefficient, soil and rock property anomaly coefficient, topographic anomaly coefficient, and groundwater anomaly coefficient are then normalized. Finally, the normalized geological structure anomaly coefficient, soil and rock property anomaly coefficient, topographic anomaly coefficient, and groundwater anomaly coefficient are used to calculate the geological environment anomaly index. The specific steps are as follows:

[0053] ;

[0054] In the formula, This is a geological environment anomaly index. This represents the geological structure anomaly coefficient. This is the anomaly coefficient of soil and rock properties. This represents the topographic anomaly coefficient. The groundwater anomaly coefficient is used to calculate the geological environment anomaly index using the formula of product plus square root. This can accurately reflect the impact of significant changes in any anomaly coefficient on the overall result. Taking the square root can balance the contribution of each coefficient, avoid the excessive dominance of any one factor, and make the final anomaly index more stable and reasonable.

[0055] In this embodiment, it should be noted that the specific steps for obtaining the sea level anomaly index are as follows:

[0056] The ocean thermal expansion coefficient is obtained by calculating the difference between the ocean thermal expansion and the seawater temperature change in the sea level data and then calculating the ratio of the difference to the seawater temperature change.

[0057] The soil and rock properties in the sea level data are obtained, and the groundwater influence coefficient is calculated by calculating the difference between the groundwater volume and soil permeability in the sea level data and then the ratio of the difference to the soil permeability.

[0058] The topography and landforms in the sea level data are obtained. The difference between the climate change data in the sea level data and the outliers in the historical climate data is calculated, and the ratio of the difference to the outliers in the historical climate data is calculated to obtain the climate change impact coefficient.

[0059] The ocean circulation influence coefficient is obtained by calculating the difference between the ocean circulation and seawater density change in the sea level data and then calculating the ratio of the difference to the seawater density change.

[0060] The ocean thermal expansion coefficient, groundwater influence coefficient, climate change influence coefficient, and ocean circulation influence coefficient are normalized. The sea level anomaly index is then calculated using these normalized coefficients. The specific steps are as follows:

[0061] ;

[0062] In the formula, Sea level anomaly index, The coefficient of thermal expansion of the ocean. The groundwater influence coefficient. The impact coefficient of climate change, The influence coefficient of ocean circulation. , , , Expressed as the normalized ocean thermal expansion coefficient, normalized groundwater influence coefficient, normalized climate change influence coefficient, and normalized ocean circulation influence coefficient, and... , , , , It is obtained through regression analysis, which is used to study the relationship between independent and dependent variables. It describes this relationship by establishing a mathematical model. The most commonly used regression analysis method is linear regression, which assumes that the relationship between independent and dependent variables is linear. Through regression analysis, the value of the dependent variable can be predicted based on known data, and the degree of influence of each independent variable on the dependent variable can be calculated.

[0063] In this embodiment, it should be noted that the specific steps for determining whether to adjust the marine data acquisition frequency based on the comprehensive disaster risk coefficient are as follows:

[0064] The system compares the comprehensive disaster risk coefficient with historical disaster warning thresholds. When the comprehensive disaster risk coefficient is greater than or equal to the historical disaster warning threshold, it is determined that there is a disaster in the marine environment, and the frequency of marine data collection is adjusted to monitor the marine disaster situation at all times. When the comprehensive disaster risk coefficient is less than the historical disaster warning threshold, data collection continues on a regular basis, thereby saving storage, computing, and energy consumption. It should be noted that the historical disaster warning threshold is obtained through statistical analysis based on historical data. Based on data and experience from past disaster events, a specific standard value or condition is set by analyzing the precursors, environmental changes, and influencing factors of disasters. When the current disaster risk index exceeds this threshold, the system will issue a disaster warning.

[0065] Step 3: If it is determined that the ocean data acquisition frequency needs to be adjusted, then the default acquisition frequency is adjusted to obtain the current acquisition frequency.

[0066] In this embodiment, it should be noted that the steps for adjusting the default sampling frequency are as follows:

[0067] When the comprehensive disaster risk coefficient is less than the historical disaster early warning threshold, the marine environment is defined as low risk, indicating that the current marine environment is stable. The marine data collection frequency is then reduced, and the specific steps to obtain the current collection frequency are as follows:

[0068] ;

[0069] In the formula, This is the current sampling frequency. This is the default sampling frequency. The incremental adjustment of the acquisition frequency under low-risk conditions should be noted. This was obtained through an analysis of the validity of historical marine environmental monitoring data and corresponding sampling frequencies. First, the completeness of monitoring data at different sampling frequencies under low-risk scenarios was statistically analyzed, and then the default sampling frequency was used as the basis for the analysis. Based on the monitoring results below, the final range was determined to be... It should be noted that the default sampling frequency The acquisition method combines the conventional marine environmental characteristics of the target sea area, takes the industry-standard basic monitoring frequency as the initial reference, and then conducts an adaptability analysis of the monitoring data density, transmission and storage costs under the historical conventional scenarios of the sea area.

[0070] When the comprehensive disaster risk coefficient is greater than or equal to the historical disaster risk threshold, the marine environment is defined as high-risk, indicating that there are disasters in the marine environment. The specific steps to obtain the current collection frequency by increasing the marine data collection frequency are as follows:

[0071] ;

[0072] In the formula, This is the current sampling frequency. This is the default sampling frequency. The incremental adjustment of the sampling frequency under high-risk conditions should be noted. The acquisition method is based on historical monitoring data from high-risk scenarios, analyzing the timeliness and accuracy of different sampling frequencies in capturing disaster precursor signals and sudden anomalies, using the default sampling frequency. Based on the monitoring and response capabilities, determine the minimum frequency increase that can significantly improve the efficiency of risk event identification.

[0073] Step four involves monitoring marine environmental data at the current collection frequency, using machine learning models to predict environmental change trends over a future period, and conducting marine disaster risk assessments based on these trends.

[0074] In this embodiment, it should be noted that the machine learning model for predicting environmental change trends over a future period is a method based on historical data and algorithm modeling. By analyzing the regularity of environmental changes, it predicts future trends to enable timely warnings and decisions. First, the machine learning model collects a large amount of historical environmental data, including meteorological data such as temperature, humidity, air pressure, precipitation, and wind speed, as well as environmental data such as ocean and soil data. Data preprocessing and feature extraction are performed. Data preprocessing includes noise removal, missing value imputation, and standardization to ensure the quality and consistency of the input data. Feature extraction extracts important features related to environmental change trends from the raw data, such as climate patterns, seasonal changes, and sudden events, for the model to learn. Next, by selecting a machine learning algorithm model, the model learns the inherent patterns in the data, allowing it to learn the relationship between input features and target values. The machine learning algorithm model will continuously train, optimize, and tune parameters to minimize prediction errors.

[0075] In conclusion, 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 principles of the present invention should be included within the protection scope of the present invention.

[0076] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for marine disaster risk assessment based on multi-parameter observation, characterized in that, Includes the following steps; Step 1: Acquire marine environmental data, meteorological data, geological data, and sea level data through ocean buoys, remote sensing satellites, earthquake and tsunami monitoring networks, and the national meteorological platform; Step 2: Calculate the marine environment anomaly index, meteorological anomaly index, geological environment anomaly index, and sea level anomaly index using marine environmental data, meteorological data, geological environmental data, and sea level height data. Then, calculate the comprehensive disaster risk coefficient based on the marine environment anomaly index, meteorological anomaly index, geological environment anomaly index, and sea level anomaly index. Finally, determine whether to adjust the marine data collection frequency based on the comprehensive disaster risk coefficient. Step 3: If it is determined that the ocean data acquisition frequency needs to be adjusted, then the default acquisition frequency is adjusted to obtain the current acquisition frequency; Step four involves monitoring marine environmental data at the current collection frequency, using machine learning models to predict environmental change trends over a future period, and conducting marine disaster risk assessments based on these trends.

2. The marine disaster risk assessment method based on multi-parameter observation according to claim 1, characterized in that: The steps for obtaining the comprehensive disaster risk coefficient are as follows: Marine environmental data is acquired, including seawater temperature, ocean current speed, sea surface pressure, and seawater density. Marine environmental anomaly indices are obtained by assessing seawater temperature, ocean current speed, sea surface pressure, and seawater density. Meteorological data is acquired, including wind speed, precipitation, cloud cover, and radiation. Meteorological anomaly indices are obtained by assessing wind speed, precipitation, cloud cover, and radiation. Geological environment data is obtained, including geological structure, soil and rock properties, topography and geomorphology, and groundwater. Geological environment anomaly index is obtained by assessing geological structure, soil and rock properties, topography and geomorphology, and groundwater. Sea level data is acquired, including data on ocean thermal expansion, groundwater volume, climate change, and ocean circulation. The sea level anomaly index is obtained by assessing ocean thermal expansion, groundwater volume, climate change, and ocean circulation. The marine environment anomaly index, meteorological anomaly index, geological environment anomaly index, and sea level anomaly index are normalized, and the comprehensive disaster risk coefficient is calculated from the normalized marine environment anomaly index, meteorological anomaly index, geological environment anomaly index, and sea level anomaly index.

3. The marine disaster risk assessment method based on multi-parameter observation according to claim 1, characterized in that: The steps for obtaining the marine environmental anomaly index are as follows: The seawater temperature is obtained from the marine environmental data. The difference between the seawater temperature in the marine data and the historical average temperature is calculated, and the ratio of the difference to the historical average temperature is calculated to obtain the seawater temperature anomaly coefficient. The ocean current velocity is obtained from the ocean data. The difference between the ocean current velocity in the ocean data and the historical average ocean current velocity is calculated, and the ratio of the difference to the historical average ocean current velocity is calculated to obtain the ocean current velocity anomaly coefficient. The sea surface pressure is obtained from the ocean data. The difference between the sea surface pressure in the ocean data and the historical average sea surface pressure is calculated, and the ratio of the difference to the historical average sea surface pressure is calculated to obtain the sea surface pressure anomaly coefficient. The seawater density is obtained from the ocean data. The difference between the seawater density in the ocean data and the historical average seawater density is calculated, and the ratio of the difference to the historical average seawater density is calculated to obtain the seawater density anomaly coefficient. The seawater temperature anomaly coefficient, ocean current velocity anomaly coefficient, sea surface air pressure anomaly coefficient, and seawater density anomaly coefficient are normalized. The normalized seawater temperature anomaly coefficient, ocean current velocity anomaly coefficient, sea surface air pressure anomaly coefficient, and seawater density anomaly coefficient are then used to calculate the marine environmental anomaly index.

4. The marine disaster risk assessment method based on multi-parameter observation according to claim 1, characterized in that: The steps for obtaining the meteorological anomaly index are as follows: obtain the wind speed from the meteorological data, calculate the difference between the wind speed in the meteorological data and the historical wind speed, and then calculate the ratio with the historical wind speed to obtain the wind speed anomaly coefficient. The precipitation data is obtained from meteorological data. The difference between the precipitation data and the historical average precipitation is calculated, and then the ratio of the difference to the historical average precipitation is calculated to obtain the precipitation anomaly coefficient. Obtain cloud cover from meteorological data, calculate the difference between cloud cover and sunshine duration, and then calculate the ratio of the difference to sunshine duration to obtain the cloud cover anomaly coefficient. The radiation in the meteorological data is obtained, and the ratio of the radiation in the meteorological data to the standard radiation value is calculated to obtain the radiation value anomaly coefficient. The wind speed anomaly coefficient, rainfall anomaly coefficient, cloud cover anomaly coefficient, and radiation value anomaly coefficient are normalized. The meteorological anomaly index is then calculated from the normalized wind speed anomaly coefficient, rainfall anomaly coefficient, cloud cover anomaly coefficient, and radiation value anomaly coefficient.

5. The marine disaster risk assessment method based on multi-parameter observation according to claim 1, characterized in that: The steps for obtaining the geological environment anomaly index are as follows: The geological structure is obtained from the geological environment data. The difference between the geological structure in the geological environment and the geological stability of the historical disaster area is calculated, and the ratio of the difference between the geological structure and the geological stability of the historical disaster area is calculated to obtain the geological structure anomaly coefficient. The rock and soil properties in the geological environment data are obtained. The difference between the rock and soil properties in the geological environment and the standard rock and soil strength is calculated, and the ratio of the difference to the standard rock and soil strength is calculated to obtain the rock and soil property anomaly coefficient. The topography and geomorphology in the geological environment data are obtained. The difference between the topography and geomorphology in the geological environment and the typical topographic risk factor is calculated, and the ratio of the difference with the typical topographic risk factor is calculated to obtain the topographic and geomorphological anomaly coefficient. The groundwater is obtained from the geological environment data. The difference between the groundwater in the geological environment and the standard groundwater level is calculated, and the ratio of the difference to the standard groundwater level is calculated to obtain the groundwater anomaly coefficient. The geological structure anomaly coefficient, soil and rock property anomaly coefficient, topographic anomaly coefficient, and groundwater anomaly coefficient are normalized. The geological environment anomaly index is then calculated from the normalized geological structure anomaly coefficient, soil and rock property anomaly coefficient, topographic anomaly coefficient, and groundwater anomaly coefficient.

6. The marine disaster risk assessment method based on multi-parameter observation according to claim 1, characterized in that: The steps for obtaining the sea level anomaly index are as follows: The ocean thermal expansion coefficient is obtained by calculating the difference between the ocean thermal expansion and the seawater temperature change in the sea level data and then calculating the ratio of the difference to the seawater temperature change. The soil and rock properties in the sea level data are obtained, and the groundwater influence coefficient is calculated by calculating the difference between the groundwater volume and soil permeability in the sea level data and then the ratio of the difference to the soil permeability. The topography and landforms in the sea level data are obtained. The difference between the climate change data in the sea level data and the outliers in the historical climate data is calculated, and the ratio of the difference to the outliers in the historical climate data is calculated to obtain the climate change impact coefficient. The ocean circulation influence coefficient is obtained by calculating the difference between the ocean circulation and seawater density change in the sea level data and then calculating the ratio of the difference to the seawater density change. The ocean thermal expansion coefficient, groundwater influence coefficient, climate change influence coefficient, and ocean circulation influence coefficient are normalized. The sea level anomaly index is then calculated using the normalized ocean thermal expansion coefficient, groundwater influence coefficient, climate change influence coefficient, and ocean circulation influence coefficient.

7. The marine disaster risk assessment method based on multi-parameter observation according to claim 1, characterized in that: The specific steps for determining whether to adjust the marine data acquisition frequency based on the comprehensive disaster risk coefficient are as follows: The comprehensive disaster risk coefficient is compared with the historical disaster warning threshold. When the comprehensive disaster risk coefficient is greater than or equal to the historical disaster warning threshold, it is determined that there is a disaster in the marine environment, and the frequency of marine data collection is adjusted. When the comprehensive disaster risk coefficient is less than the historical disaster warning threshold, timed data collection continues.

8. The marine disaster risk assessment method based on multi-parameter observation according to claim 1, characterized in that: The steps for adjusting the default sampling frequency are as follows: When the comprehensive disaster risk coefficient is less than the historical disaster early warning threshold, the marine environment is defined as low risk, and the marine data collection frequency is reduced to obtain the current collection frequency. The specific steps for obtaining this frequency are as follows: ； In the formula, This is the current sampling frequency; the default sampling frequency is also available. Adjust the sampling frequency increment for low-risk conditions; When the comprehensive disaster risk coefficient is greater than or equal to the historical disaster risk threshold, the marine environment is defined as high-risk. The frequency of marine data collection is increased to obtain the current collection frequency. The specific steps for obtaining this frequency are as follows: ; In the formula, This is the current sampling frequency. This is the default sampling frequency. Adjust the sampling frequency increment for high-risk conditions.

Images