Marine ecological environment simulation method and system based on big data analysis
Through the method based on big data analysis, the temperature state of the sea area and the transfer probability matrix are defined, which solves the problems of lack of parameters and difficulty in short-term temperature monitoring in the marine ecological model, and improves the accuracy of ecological environment simulation.
Patent Information
- Application Number
- CN202411140268.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-20
AI Technical Summary
The lack of biochemical process parameters and short-term seawater temperature monitoring methods for specific sea areas in the existing marine ecological models makes it difficult to improve the accuracy of ecological environment simulation results.
The seasonal state, depth state and daily change state of the temperature change in the target sea area are defined by the classification and transfer probability matrix of historical temperature data, and the short-term changes in seawater temperature are simulated using the Markov chain model.
The accuracy of short-term ecological environment simulation results is improved, and the impact of seasonal, depth and daily changes on seawater temperature is taken into account, and the seawater temperature factor data is provided for building marine ecological environment models.
Smart Images

Figure CN118656998B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of marine ecological environment, and in particular to a marine ecological environment simulation method and system based on big data analysis. Background Art
[0002] The ocean is the largest ecosystem on Earth and plays a vital role in maintaining the ecological balance of the Earth and regulating the Earth's climate. Protecting the marine ecological environment and maintaining the marine ecological balance are related to the balance of the Earth's ecosystem and the quality of human living environment. The acquisition of marine physical elements such as seawater temperature, salinity, and flow field is the basis and key to building a marine ecological environment simulation model.
[0003] The lack of observational data has always been a problem that has plagued the marine ecology community. Wei Hao once pointed out that in the existing marine ecological models, there is a lack of biochemical process parameters for specific sea areas; Zhang Suxiang believes that the lack of parameters makes it difficult to improve the accuracy of simulation results; Wang Hui once pointed out that under the current level of development of ecological dynamics models in my country, field survey plans should be designed according to the characteristics of the ecosystem, and advanced sampling and analysis methods should be adopted. At the same time, data processing methods such as parameter optimization technology should be developed to maximize the use of existing data and provide a basis for the development of models.
[0004] Among them, seawater temperature, as an important observation parameter, plays a decisive role in whether the ecological environment simulation model can be successfully constructed. In terms of macro trends, the change of seawater temperature shows periodic changes with the seasons, but it will be affected by many factors in the short term. In the existing technology, there is a lack of effective means for short-term monitoring of seawater temperature elements, which will make the simulation results of the ecological environment in the short term less accurate. To this end, we propose a marine ecological environment simulation method and system based on big data analysis. Summary of the invention
[0005] The main purpose of the present invention is to provide a method and system for simulating the marine ecological environment based on big data analysis, which can effectively solve the problems in the background technology.
[0006] In order to achieve the above object, the technical solution adopted by the present invention is:
[0007] Marine ecological environment simulation methods based on big data analysis include:
[0008] Step S1: define the seasonal state of temperature change in the target sea area as λ, the depth state as μ, and the daily change state as θ, where λ∈{1,2,...,12}; μ∈{H,L}, H represents the high depth state, and L represents the low depth state; θ∈{θ1,θ2,θ3,θ4};
[0009] The definition principles are:
[0010] For the seasonal state λ: divide a year cycle into 12 monthly units according to the month, and let each monthly unit correspond to a seasonal state, then λ∈{1,2,...,12};
[0011] For the depth state μ: obtain the historical depth data of the target sea area and calculate the average depth value ,in, , is the kth sampling value in the historical depth data of the target sea area, n is the number of sampling times, when the depth value of the target sea area is greater than the average depth value When , the depth state is determined to be a high depth state, otherwise, the depth state is determined to be a low depth state;
[0012] Daily variation state θ: According to the solar radiation intensity of the target sea area, a daily cycle is divided into four time periods: 00:00-06:00, 06:00-12:00, 12:00-18:00, and 18:00-24:00, corresponding to the four daily variation states of θ1, θ2, θ3, and θ4 respectively;
[0013] Step S2: Obtain the historical temperature data sequence T of the target sea area, and divide the temperature range of the target sea area into s states;
[0014] The segmentation process includes the following steps:
[0015] Obtain the historical temperature data sequence T of the target sea area and obtain the statistical values of the data sequence T, including the maximum temperature value t max , minimum temperature value t min , total data Q, data frequency q corresponding to the temperature value;
[0016] Randomly select s-2 values between the maximum temperature value t in the data sequence T max and minimum temperature t min The intermediate temperature values between are denoted as t1, t2, ..., t s-2 , where s-2 is a positive integer and s<Q-2; t min <t1<t2<...<t s-2 <t max ;
[0017] Classify the temperature values in the data sequence T into , ,..., , The data frequency q corresponding to the temperature value in each interval is obtained respectively. min ,q m ,q max , where q min For The frequency of temperature values in the interval; q m For The frequency of temperature values in the interval; q max For The frequency of temperature values in the interval; m is a positive integer, m≤s-2; Q=q min + +q max ;
[0018] Get the current q min =q1=q2=...=q s-2 =q max The corresponding temperature values are t1, t2, ..., t s-2 , that is, to obtain the classification interval , ,..., , , corresponding to the s states of the target sea temperature range;
[0019] Step S3: Classify the historical temperature data sequence T according to the seasonal state, depth state, and daily change state at the time of measurement to obtain the classified historical temperature data sequence ;
[0020] Step S4: According to the classified historical temperature data sequence Calculate the temperature transfer probability of the target sea area , the calculation formula is: , where is the historical temperature data series The frequency of the temperature of the target sea area directly transferring from state i to state j;
[0021] Step S5: Construct the corresponding transition probability matrix according to the temperature transition probability of the target sea area obtained , where the expression of the transition probability matrix is: ;
[0022] Step S6: simulating the temperature of the target sea area according to the obtained transition probability matrix, obtaining the temperature value of the target sea area in the next cycle, and constructing a simulated time series of the temperature value of the target sea area;
[0023] The specific process includes the following steps:
[0024] Step S61: Obtain the temperature value t of the target sea area at the current time t t and seawater depth d t , according to the temperature value t t Determine the current temperature state is m t , according to the data acquisition time t and seawater depth d tDetermine the current season state λ t , depth state μ t 、Daily change state θ t ;
[0025] Step S62: Select the seasonal state λ t , depth state μ t 、Daily change state θ t The corresponding transition probability matrix ; Calculate the cumulative transition probability matrix ,in, ;
[0026] Step S63: According to the temperature state m at the current time t t Generate a random number ω from a uniform distribution t , and ω t ∈ , according to the random number ω t The next state m of the current target sea area temperature is determined by comparing the result with the temperature state transition probability. t+1 , the judgment principle is:
[0027] If 0≤ω t ≤ , then the next state m of the current target sea area temperature t+1 =1;
[0028] like <ω t ≤ , then the next state m of the current target sea area temperature t+1 =σ+1;
[0029] Step S64: Calculate the temperature value of the target sea area in the next state according to the result of the next state of the temperature, specifically:
[0030] According to the temperature state m t+1 Generate a random number ω from a uniform distribution t+1 , and ω t+1 ∈ ;
[0031] Get temperature status m t+1 The corresponding temperature value classification interval, where , They are temperature states m t+1 The minimum and maximum values of the corresponding temperature classification interval;
[0032] According to the random number ω t+1 and temperature state m t+1 The corresponding temperature value classification interval , calculate the temperature value t under this temperature statet+1 , the calculation formula is: ;
[0033] Step S7: Using the obtained temperature value simulation time series of the target sea area as observation data to simulate the ecological environment of the target sea area.
[0034] The marine ecological environment simulation system based on big data analysis includes a historical temperature data acquisition module, a characteristic state definition module, a temperature state definition module, a temperature data processing module, a temperature state transfer model construction module, and an ecological environment simulation module;
[0035] The historical temperature data acquisition module is used to acquire the historical temperature data sequence T of the target sea area;
[0036] The characteristic state definition module is used to define the characteristic state of the temperature change of the target sea area, wherein the characteristic state includes the seasonal state λ, the depth state μ, and the daily change state θ;
[0037] The temperature state definition module is used to divide the temperature interval state of the target sea area;
[0038] The temperature data processing module is used to classify the historical temperature data sequence T according to the seasonal state, depth state, and daily change state at the time of measurement, and obtain the classified historical temperature data sequence ;
[0039] The temperature state transfer model building module is used to classify the historical temperature data sequence Construct a transfer probability matrix, and simulate the temperature of the target sea area according to the obtained transfer probability matrix to obtain the temperature value of the target sea area in the next cycle;
[0040] The ecological environment simulation module is used to simulate the ecological environment of the target sea area by using the simulated time series of the temperature values of the target sea area as observation data.
[0041] The system also includes a memory, a processor, and a computer program stored on the memory and executable on the processor.
[0042] The present invention has the following beneficial effects:
[0043] Compared with the prior art, the seasonal state, depth state and daily change state of the temperature change in the target sea area are defined, the historical temperature data sequence T of the target sea area is obtained, the temperature range of the target sea area is divided into s states, the historical temperature data sequence T is classified according to the seasonal state, depth state and daily change state during measurement, and the classified historical temperature data sequence is obtained. The temperature transition probability of the target sea area is calculated according to the classified historical temperature data sequence, and a corresponding transition probability matrix is constructed according to the obtained temperature transition probability of the target sea area. The temperature of the target sea area is simulated according to the obtained transition probability matrix, the temperature value of the target sea area in the next period is obtained, and a temperature value simulation time series of the target sea area is constructed. The ecological environment of the target sea area is simulated using the obtained temperature value simulation time series of the target sea area as observation data, and the influence of the seasonal state, depth state and daily change state on the seawater temperature is considered. Based on big data analysis and Markov chain model, seawater temperature element data for constructing a marine ecological environment simulation model are obtained, which is conducive to improving the accuracy of short-term ecological environment simulation results. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 This is a flow chart of the marine ecological environment simulation method based on big data analysis of the present invention;
[0045] Figure 2 This is a structural block diagram of the marine ecological environment simulation system based on big data analysis of the present invention. DETAILED DESCRIPTION
[0046] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.
[0047] The implementation process of the technical solution of the present invention includes the following steps:
[0048] Step 1: Define the seasonal state of temperature change in the target sea area as λ, the depth state as μ, and the daily change state as θ, where λ∈{1,2,...,12}; μ∈{H,L}, H represents the high depth state and L represents the low depth state; θ∈{θ1,θ2,θ3,θ4};
[0049] The definition principles are:
[0050] For the seasonal state λ: divide a year cycle into 12 monthly units according to the month, and let each monthly unit correspond to a seasonal state, then λ∈{1,2,...,12};
[0051] For the depth state μ: obtain the historical depth data of the target sea area and calculate the average depth value ,in, , is the kth sampling value in the historical depth data of the target sea area, n is the number of sampling times, when the depth value of the target sea area is greater than the average depth value When , the depth state is determined to be a high depth state, otherwise, the depth state is determined to be a low depth state;
[0052] Daily variation state θ: According to the solar radiation intensity of the target sea area, a daily cycle is divided into four time periods: 00:00-06:00, 06:00-12:00, 12:00-18:00, and 18:00-24:00, corresponding to the four daily variation states of θ1, θ2, θ3, and θ4 respectively;
[0053] Step 2: Obtain the historical temperature data sequence T of the target sea area and divide the temperature range of the target sea area into s states;
[0054] The segmentation process includes the following steps:
[0055] Obtain the historical temperature data sequence T of the target sea area and obtain the statistical values of the data sequence T, including the maximum temperature value t max , minimum temperature value t min , total data Q, data frequency q corresponding to the temperature value;
[0056] Randomly select s-2 values between the maximum temperature value t in the data sequence T max and minimum temperature t min The intermediate temperature values between are denoted as t1, t2, ..., t s-2 , where s-2 is a positive integer and s<Q-2; t min <t1<t2<...<t s-2 <t max ;
[0057] Classify the temperature values in the data sequence T into , ,..., , The data frequency q corresponding to the temperature value in each interval is obtained respectively. min ,q m ,q max , where q min For The frequency of temperature values in the interval; q m For The frequency of temperature values in the interval; q max For The frequency of temperature values in the interval; m is a positive integer, m≤s-2; Q=q min + +q max ;
[0058] Get the current q min =q1=q2=...=q s-2 =q max The corresponding temperature values are t1, t2, ..., t s-2 , that is, to obtain the classification interval , ,..., , , corresponding to the s states of the target sea temperature range;
[0059] Step 3: Classify the historical temperature data sequence T according to the seasonal state, depth state, and daily change state at the time of measurement to obtain the classified historical temperature data sequence ;
[0060] Step 4: Based on the classified historical temperature data series Calculate the temperature transfer probability of the target sea area , the calculation formula is: , where is the historical temperature data series The frequency of the temperature of the target sea area directly transferring from state i to state j;
[0061] Step 5: Construct the corresponding transition probability matrix based on the temperature transition probability of the target sea area , where the expression of the transition probability matrix is: ;
[0062] Step 6: Simulate the temperature of the target sea area according to the obtained transition probability matrix, obtain the temperature value of the target sea area in the next cycle, and construct a simulated time series of the temperature value of the target sea area;
[0063] The specific process includes the following steps:
[0064] Get the temperature value t of the target sea area at the current time t t and seawater depth d t , according to the temperature value t t Determine the current temperature state is m t , according to the data acquisition time t and seawater depth d t Determine the current season state λ t , depth state μ t 、Daily change state θ t ;
[0065] Selection and Seasonal State λt , depth state μ t 、Daily change state θ t The corresponding transition probability matrix ; Calculate the cumulative transition probability matrix ,in, ;
[0066] According to the temperature state m at the current time t t Generate a random number ω from a uniform distribution t , and ω t ∈ , according to the random number ω t The next state m of the current target sea area temperature is determined by comparing the result with the temperature state transition probability. t+1 , the judgment principle is:
[0067] If 0≤ω t ≤ , then the next state m of the current target sea area temperature t+1 =1;
[0068] like <ω t ≤ , then the next state m of the current target sea area temperature t+1 =σ+1;
[0069] Step S64: Calculate the temperature value of the target sea area in the next state according to the result of the next state of the temperature, specifically:
[0070] According to the temperature state m t+1 Generate a random number ω from a uniform distribution t+1 , and ω t+1 ∈ ;
[0071] Get temperature status m t+1 The corresponding temperature value classification interval, where , They are temperature states m t+1 The minimum and maximum values of the corresponding temperature classification interval;
[0072] According to the random number ω t+1 and temperature state m t+1 The corresponding temperature value classification interval , calculate the temperature value t under this temperature state t+1 , the calculation formula is: ;
[0073] Step 7: Use the simulated time series of the temperature values of the target sea area as observation data to simulate the ecological environment of the target sea area.
[0074] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A marine ecological environment simulation method based on big data analysis, characterized in that: include: Step S1: define the seasonal state of temperature change in the target sea area as λ, the depth state as μ, and the daily change state as θ, where λ∈{1,2,...,12}; μ∈{H,L}, H represents the high depth state, and L represents the low depth state; θ∈{θ1,θ2,θ3,θ4}; Step S2: Obtain the historical temperature data sequence T of the target sea area, and divide the temperature range of the target sea area into s states; Step S3: Classify the historical temperature data sequence T according to the seasonal state, depth state, and daily change state at the time of measurement, and obtain the classified historical temperature data sequence T λ,μ,θ ; Step S4: According to the classified historical temperature data sequence T λ,μ,θ Calculate the temperature transfer probability of the target sea area The calculation formula is: In the formula, is the historical temperature data series T λ,μ,θ The frequency of the temperature of the target sea area directly transferring from state i to state j; Step S5: Construct the corresponding transition probability matrix P according to the temperature transition probability of the target sea area obtained λ,μ,θ , where the expression of the transition probability matrix is: Step S6: simulating the temperature of the target sea area according to the obtained transition probability matrix, obtaining the temperature value of the target sea area in the next cycle, and constructing a simulated time series of the temperature value of the target sea area; Step S7: Using the obtained temperature value simulation time series of the target sea area as observation data to simulate the ecological environment of the target sea area. The definition principles of the seasonal state λ, depth state μ, and daily variation state θ of the target sea area are as follows: For the seasonal state λ: divide a year cycle into 12 monthly units according to the month, and let each monthly unit correspond to a seasonal state, then λ∈{1,2,...,12}; For the depth state μ: obtain the historical depth data of the target sea area and calculate the average depth value in, Dv k is the kth sampling value in the historical depth data of the target sea area, n is the number of sampling times, when the depth value of the target sea area is greater than the average depth value When , the depth state is determined to be a high depth state, otherwise, the depth state is determined to be a low depth state; Daily variation state θ: According to the solar radiation intensity of the target sea area, a daily cycle is divided into four time periods: 00:00-06:00, 06:00-12:00, 12:00-18:00, and 18:00-24:00, corresponding to the four daily variation states of θ1, θ2, θ3, and θ4 respectively; The temperature range state division process includes the following steps: Obtain the historical temperature data sequence T of the target sea area and obtain the statistical values of the data sequence T, including the maximum temperature value t max , minimum temperature value t min , total data Q, data frequency q corresponding to the temperature value; Randomly select s-2 values between the maximum temperature value t in the data sequence T max and minimum temperature t min The intermediate temperature values between are denoted as t1, t2, ..., t s-2 , where s-2 is a positive integer and s<Q-2; t min <t1<t2<...<t s-2 <t max ; Classify the temperature values in the data sequence T into [t min , t1), [t1, t2), ..., [t s-3 , t s-2 ),[t s-2 , t max ] interval, and obtain the data frequency q corresponding to the temperature value in each interval segment respectively min ,q m ,q max , where q min For the min , t1) the frequency of temperature values in the interval; q m For the m-1 , t m ) The frequency of temperature values in the interval; q max For the m , t max ] is the frequency of temperature values in the interval; and m is a positive integer, m≤s-2; Get the current q min =q1=q2=...=q s-2 =q max The corresponding temperature values are t1, t2, ..., t s-2 , that is, to obtain the classification interval [t min , t1), [t1, t2), ..., [t s-3 , t s-2 ),[t s-2 , t max ], corresponding to the s states of the target sea temperature range; The specific process of step S6 includes the following steps: Step S61: Obtain the temperature value t of the target sea area at the current time t t and seawater depth d t , according to the temperature value t t Determine the current temperature state is m t , according to the data acquisition time t and seawater depth d t Determine the current season state λ t , depth state μ t 、Daily change state θ t ; Step S62: Select the seasonal state λ t , depth state μ t 、Daily change state θ t The corresponding transition probability matrix Calculate the cumulative transition probability matrix in, Step S63: According to the temperature state m at the current time t t Generate a random number ω from a uniform distribution t , and ω t ∈[0, 1], according to the random number ω t The next state m of the current target sea area temperature is determined by comparing the result with the temperature state transition probability. t+1 , the judgment principle is: like Then the next state m of the current target sea area temperature t+1 =1; like Then the next state m of the current target sea area temperature t+1 =σ+1; Step S64: Calculate the temperature value of the target sea area in the next state according to the result of the next state of the temperature, specifically: According to the temperature state m t+1 Generate a random number ω from a uniform distribution t+1 , and ω t+1 ∈[0, 1]; Get temperature status m t+1 The corresponding temperature value classification interval, where They are temperature states m t+1 The minimum and maximum values of the corresponding temperature classification interval; According to the random number ω t+1 and temperature state m t+1 The corresponding temperature value classification interval Calculate the temperature value t under this temperature state t+1 , the calculation formula is:
2. Marine ecological environment simulation system based on big data analysis, characterized by: The system includes a historical temperature data acquisition module, a characteristic state definition module, a temperature state definition module, a temperature data processing module, a temperature state transfer model construction module, and an ecological environment simulation module; The historical temperature data acquisition module is used to acquire the historical temperature data sequence T of the target sea area; The characteristic state definition module is used to define the characteristic state of the temperature change in the target sea area, wherein the characteristic state includes the seasonal state λ, the depth state μ, and the daily change state θ, and the definition principle is: For the seasonal state λ: divide a year cycle into 12 monthly units according to the month, and let each monthly unit correspond to a seasonal state, then λ∈{1,2,...,12}; For the depth state μ: obtain the historical depth data of the target sea area and calculate the average depth value in, Dv k is the kth sampling value in the historical depth data of the target sea area, n is the number of sampling times, when the depth value of the target sea area is greater than the average depth value When , the depth state is determined to be a high depth state, otherwise, the depth state is determined to be a low depth state; The temperature state definition module is used to divide the temperature range of the target sea area into s states, wherein the division process includes the following steps: Obtain the historical temperature data sequence T of the target sea area and obtain the statistical values of the data sequence T, including the maximum temperature value t max , minimum temperature value t min , total data Q, data frequency q corresponding to the temperature value; Randomly select s-2 values between the maximum temperature value t in the data sequence T max and minimum temperature t min The intermediate temperature values between are denoted as t1, t2, ..., t s-2 , where s-2 is a positive integer and s<Q-2; t min <t1<t2<...<t s-2 <t max ; Classify the temperature values in the data sequence T into [t min , t1), [t1, t2), ..., [t s-3 , t s-2 ),[t s-2 , t max ] interval, and obtain the data frequency q corresponding to the temperature value in each interval segment respectively min ,q m ,q max , where q min For the min , t1) the frequency of temperature values in the interval; q m For the m-1 , t m ) The frequency of temperature values in the interval; q max For the m , t max ] is the frequency of temperature values in the interval; and m is a positive integer, m≤s-2; Get the current q min =q1=q2=...=q s-2 =q max The corresponding temperature values are t1, t2, ..., t s-2 , that is, to obtain the classification interval [t min , t1), [t1, t2), ..., [t s-3 , t s-2 ),[t s-2 , t max ], corresponding to the s states of the target sea temperature range; The temperature data processing module is used to classify the historical temperature data sequence T according to the seasonal state, depth state, and daily change state at the time of measurement, and obtain the classified historical temperature data sequence T λ,μ,θ ; The temperature state transfer model building module is used to classify the historical temperature data sequence T λ,μ,θ Construct a transfer probability matrix, and simulate the temperature of the target sea area according to the obtained transfer probability matrix to obtain the temperature value of the target sea area in the next cycle; Among them, the specific steps of the transition probability matrix construction process are: According to the classified historical temperature data sequence T λ,μ,θ Calculate the temperature transfer probability of the target sea area The calculation formula is: In the formula, is the historical temperature data series T λ,μ,θ The frequency of the temperature of the target sea area directly transferring from state i to state j; According to the temperature transfer probability of the target sea area, the corresponding transfer probability matrix P is constructed. λ,μ,θ , where the expression of the transition probability matrix is: The specific steps of the temperature simulation process of the target sea area are: Get the temperature value t of the target sea area at the current time t t and seawater depth d t , according to the temperature value t t Determine the current temperature state is m t , according to the data acquisition time t and seawater depth d t Determine the current season state λ t , depth state μ t 、Daily change state θ t ; Selection and Seasonal State λ t , depth state μ t 、Daily change state θ t The corresponding transition probability matrix Calculate the cumulative transition probability matrix in, According to the temperature state m at the current time t t Generate a random number ω from a uniform distribution t , and ω t ∈[0, 1], according to the random number ω t The next state m of the current target sea area temperature is determined by comparing the result with the temperature state transition probability. t+1 , the judgment principle is: like Then the next state m of the current target sea area temperature t+1 =1; like Then the next state m of the current target sea area temperature t+1 =σ+1; The temperature value of the target sea area in this state is calculated according to the result of the next state of the temperature, specifically: According to the temperature state m t+1 Generate a random number ω from a uniform distribution t+1 , and ω t+1 ∈[0, 1]; Get temperature status m t+1 The corresponding temperature value classification interval, where They are temperature states m t+1 The minimum and maximum values of the corresponding temperature classification interval; According to the random number ω t+1 and temperature state m t+1 The corresponding temperature value classification interval Calculate the temperature value t under this temperature state t+1 , the calculation formula is: The ecological environment simulation module is used to simulate the ecological environment of the target sea area by using the simulated time series of the temperature values of the target sea area as observation data.
3. The marine ecological environment simulation system based on big data analysis according to claim 2 is characterized in that: The system further comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the method described in claim 1 are implemented when the processor executes the program.
Citation Information
Patent Citations
Method for simulation generation of wind power times series based on improved Markov chain
CN107103411A
Shallow seawater temperature space-time prediction method
CN115729977A
