Seabed inversion method, device and equipment based on genetic clone selection and medium

Abstract

The invention discloses a seabed inversion method, device and equipment based on genetic clone selection and a medium, and the method comprises the steps: carrying out the initialization to obtain a first population, and taking the first population as a target population; performing inversion and evaluation based on the inversion parameters of the target population to obtain a root-mean-square value corresponding to each individual; setting random parameters based on the minimum root-mean-square value and population iteration times; performing population updating based on a random parameter improved genetic algorithm; when the root mean square value in the updated population accords with the iterative optimal threshold value, taking the corresponding individual as a target individual; otherwise, population updating is carried out circularly until the target individual is obtained, or the number of population iterations is equal to the preset maximum number of population iterations; and finally, according to the submarine topography data corresponding to the target individual, determining a submarine inversion result of the to-be-inverted region. The method can accurately realize seabed inversion, and can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a seafloor inversion method, device, equipment and medium based on genetic clonal selection. Background Art

[0002] At present, with the continuous development of geophysical exploration technology, the demand for accurate inversion of crustal structure, especially Moho depth, is becoming increasingly urgent. As a classic in the field of interface inversion, the Parker-Oldenburg method has been widely used in the industry due to its efficient computing performance based on fast Fourier transform (FFT). However, when using this method, the existing technical solutions generally treat the inversion parameters as fixed constants, which is inadequate when facing complex and changeable underground geological conditions. Specifically, the density difference and depth of the underground medium are not a simple linear relationship, but are affected by a combination of various geological factors. Therefore, fixing the parameters will inevitably lead to the loss of accuracy of the inversion results. In addition, the existing solutions also have shortcomings in terms of computational efficiency and degree of automation, such as large overall computational complexity and lack of a unified execution framework, which have an adverse effect on the accuracy and practicality of the inversion results. Summary of the invention

[0003] The present invention aims to solve the problem of related technical limitations at least to a certain extent. To this end, the present invention proposes a seafloor inversion method, device, equipment and medium based on genetic clonal selection, which can accurately perform seafloor inversion.

[0004] On the one hand, an embodiment of the present invention provides a seafloor inversion method based on genetic clonal selection, comprising:

[0005] A first number of inversion parameters are randomly generated in a first interval, and a first population is obtained based on the initialization of the inversion parameters; the first population is used as a target population; the number of iterations of the initialization population is 1; wherein the inversion parameters correspond to individuals in the target population; and the inversion parameters include density difference and seafloor depth;

[0006] Inverting the inversion parameters of each individual in the target population to obtain first seafloor topography data of the area to be inverted; processing the first seafloor topography data and the seismic depth matrix of the area to be inverted to obtain a first root mean square value corresponding to each individual in the target population; and using the first root mean square value as a target root mean square value;

[0007] Obtain the minimum RMS value among the target RMS values ​​corresponding to all individuals in the target population, and set random parameters based on the minimum RMS value and the number of population iterations;

[0008] Obtain individuals corresponding to the target root mean square value of each stage range from the target population and mix them to obtain a second number of crossover individuals; the crossover individuals include two individuals;

[0009] Based on a preset crossover ratio, a weighted crossover operation is performed on the crossover individual to obtain a first sub-individual;

[0010] Obtain a set of individuals to be mutated from the target population based on probability, perform a mutation operation on each individual in the set of individuals based on a preset mutation random number, and obtain a corresponding second child individual;

[0011] A second population is obtained by sorting out all first sub-individuals, all second sub-individuals and the target population; second seafloor topographic data of the area to be inverted is obtained based on the inversion parameters corresponding to each individual in the second population; a second root mean square value corresponding to each individual in the second population is obtained based on the second seafloor topographic data and seismic depth matrix processing;

[0012] When there is a second RMS value in the second population that is less than or equal to the iterative optimal threshold, the corresponding individual is taken as the target individual; otherwise,

[0013] A third number of individuals are selected from the second population based on probability to obtain a third population, the third population is used as the target population, the second RMS value is used as the target RMS value, the number of population iterations is increased by 1, and the step of obtaining the minimum RMS value among the target RMS values ​​corresponding to all individuals in the target population is returned to execute until the target individual is obtained, or the number of population iterations is equal to the preset maximum number of population iterations;

[0014] When the number of population iterations is equal to the maximum number of population iterations, the target individual is output according to the target population obtained in the last cycle;

[0015] The second seafloor topographic data corresponding to the target individual is used as the seafloor inversion result of the area to be inverted.

[0016] Optionally, setting random parameters based on the minimum root mean square value and the number of population iterations includes the following steps:

[0017] Based on the population iteration number and the minimum RMS value, the random parameters are obtained in combination with the preset genetic parameter settings;

[0018] Among them, the genetic parameters include the optimal threshold of iteration, the maximum number of iterations of the population and the probability adjustment factor; the expression of the random parameter is:

[0019]

[0020] Wherein, sigma represents the random parameter; minIterDelt represents the iterative optimal threshold; e represents the natural constant; iter represents the number of population iterations; maxGenCnt represents the maximum number of population iterations; F1 represents the probability adjustment factor; curMinRMS represents the minimum RMS value among the target RMS values.

[0021] Optionally, obtaining individuals corresponding to the target root mean square value of each stage range from the target population and mixing them to obtain a second number of crossover individuals includes the following steps:

[0022] Traverse the target RMS values ​​of all individuals in the target population, sort all individuals in the target population from small to large according to the target RMS values, and obtain the first sequence population;

[0023] All individuals of the first sequence population are equally divided based on the arrangement order to obtain multiple individual groups, and all pairing situations of any two individual groups are determined;

[0024] From each pairing situation, obtain the corresponding number of crossover individuals in the group;

[0025] The number of groups is determined based on the ratio of the second number to the total number of pairing situations, and the two individuals of the crossover individuals are respectively taken from the two individual groups of the corresponding pairing situations.

[0026] Optionally, the crossover individual includes a first individual and a second individual; based on a preset crossover ratio, performing a weighted crossover operation on the crossover individual to obtain a first sub-individual includes the following steps:

[0027] Based on the random parameters, the crossover ratio is obtained in combination with the preset crossover operator ratio setting;

[0028] The expression of the crossover ratio is:

[0029] β=crossoverAlpha+normal(0,sigma);

[0030] In the formula, β represents the crossover operator; crossoverAlpha represents the crossover operator ratio; crossoverAlpha is a constant; sigma represents a random parameter; normal(0,sigma) means that 0 is the mean and sigma is a random value of the standard deviation;

[0031] Based on the crossover ratio, weighted addition is performed on the inversion parameters corresponding to the first individual and the second individual to obtain the inversion parameters of the first sub-individual;

[0032] Among them, the expression of the inversion parameter of the first sub-individual is:

[0033] A3=A1*β+A2*(1-β);

[0034] Where A3 represents the inversion parameters of the first sub-individual; A1 represents the inversion parameters of the first individual; A2 represents the inversion parameters of the second individual.

[0035] Optionally, obtaining a set of individuals to be mutated from a target population based on probability includes the following steps:

[0036] Traverse each individual in the target population, and set the mutation probability of each individual in turn based on the target RMS value combined with the random parameters;

[0037] Among them, the expression of mutation probability is:

[0038]

[0039] In the formula, prob represents the probability of mutation; sigma represents the random parameter; RMS represents the target root mean square value of the corresponding individual;

[0040] The first individual of the target population is used as the individual to be mutated;

[0041] Generate a random number in the second interval as a mutation parameter;

[0042] When the mutation parameter is less than the mutation probability corresponding to the individual to be mutated, the individual to be mutated is sorted into the individual set; otherwise, the next individual of the individual to be mutated in the target population is taken as the individual to be mutated, and the step of generating a random number as the mutation parameter in the second interval is returned to execute until all individuals in the target population are traversed and the individual set is output.

[0043] Optionally, performing a mutation operation on each individual in the individual set based on a preset mutation random number to obtain a corresponding second child individual includes the following steps:

[0044] Take the first individual in the individual set as the mutant individual;

[0045] Generate mutated random numbers with 0 as mean and random parameter as standard deviation;

[0046] Based on the product of the mutated random number and the interval range difference of the first interval, the inversion parameter corresponding to the mutated individual is mutated and assigned, so as to obtain the inversion parameter of the second sub-individual;

[0047] Among them, the expression of the inversion parameter of the second sub-individual is:

[0048] A4=A1+(max-mix)*normal(0,sigma);

[0049] Where A4 represents the inversion parameter of the second sub-individual; A1 represents the inversion parameter of the mutant individual; max represents the maximum value of the first interval; min represents the minimum value of the first interval; normal(0, sigma) represents the mutant random number.

[0050] Optionally, selecting a third number of individuals from the second population based on probability to obtain a third population comprises the following steps:

[0051] Get the population size of the second population;

[0052] Based on the random parameter and the population size, a third size is obtained in combination with a preset population size adjustment factor setting;

[0053] The expression of the third quantity is:

[0054] newSizePop=max(curPopSize*F2,curPopSize+F2*curPopSize*normal(0,sigma));

[0055] Wherein, newSizePop represents the third quantity; curPopSize represents the population size; F2 represents the population size adjustment factor; sigma represents a random parameter; normal(0,sigma) represents a random value with 0 as the mean and sigma as the standard deviation; max(X,Y) represents the maximum value of X and Y;

[0056] Traverse the second root mean square values ​​of all individuals in the second population, sort all individuals in the second population from small to large according to the second root mean square values, and obtain a second sequence population;

[0057] Select a fourth number of individuals from the pre-sequence of the second sequence population as the first candidate individual set; the fourth number is half of the third number;

[0058] Randomly selecting a fourth number of individuals from the individuals other than the first candidate individual set in the second sequence population as the second candidate individual set;

[0059] The third population is obtained by sorting the first candidate individual set and the second candidate individual set.

[0060] On the other hand, an embodiment of the present invention provides a seafloor inversion device based on genetic cloning selection, comprising:

[0061] The first module is used to randomly generate a first number of inversion parameters in a first interval, and obtain a first population based on the inversion parameters initialization; the first population is used as a target population; the number of population iterations is initialized to 1; wherein the inversion parameters correspond to individuals in the target population; the inversion parameters include density difference and seafloor depth;

[0062] The second module is used to obtain first seafloor topographic data of the area to be inverted based on the inversion parameters of each individual in the target population; obtain a first root mean square value corresponding to each individual in the target population based on the first seafloor topographic data and the seismic depth matrix of the area to be inverted; and use the first root mean square value as the target root mean square value;

[0063] The third module is used to obtain the minimum root mean square value among the target root mean square values ​​corresponding to all individuals in the target population, and set random parameters based on the minimum root mean square value and the number of population iterations;

[0064] The fourth module is used to obtain individuals corresponding to the target root mean square value of each stage range from the target population and mix them to obtain a second number of crossover individuals; the crossover individuals include two individuals;

[0065] The fifth module is used to perform a weighted crossover operation on the crossover individual based on a preset crossover ratio to obtain a first sub-individual;

[0066] The sixth module is used to obtain a set of individuals to be mutated from the target population based on probability, and perform a mutation operation on each individual in the set of individuals based on a preset mutation random number to obtain a corresponding second child individual;

[0067] The seventh module is used to obtain a second population according to all the first sub-individuals, all the second sub-individuals and the target population; obtain the second seafloor topographic data of the area to be inverted based on the inversion parameters corresponding to each individual in the second population; obtain the second root mean square value corresponding to each individual in the second population based on the second seafloor topographic data and seismic depth matrix processing;

[0068] The eighth module is used to take the corresponding individual as the target individual when the second RMS value in the second population is less than or equal to the iterative optimal threshold; otherwise,

[0069] A ninth module is used for selecting a third number of individuals from the second population based on probability to obtain a third population, taking the third population as the target population, taking the second root mean square value as the target root mean square value, increasing the number of population iterations by 1, and returning to execute the third module until the target individual is obtained, or the number of population iterations is equal to the preset maximum number of population iterations;

[0070] The tenth module is used to output the target individual according to the target population obtained in the last cycle when the number of population iterations is equal to the maximum number of population iterations;

[0071] The eleventh module is used to use the second seafloor topographic data corresponding to the target individual as the seafloor inversion result of the area to be inverted.

[0072] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store programs; the processor executes the program to implement the above-mentioned seabed inversion method based on genetic clonal selection.

[0073] On the other hand, an embodiment of the present invention provides a computer storage medium storing a program executable by a processor, and the program executable by the processor is used to implement the above-mentioned seafloor inversion method based on genetic clonal selection when executed by the processor.

[0074] The embodiment of the present invention randomly generates a first number of inversion parameters in a first interval, and obtains a first population based on the initialization of the inversion parameters; takes the first population as the target population; initializes the population iteration number to 1; wherein the inversion parameters correspond to individuals in the target population; the inversion parameters include density difference and seafloor depth; obtains first seafloor topography data of the area to be inverted based on the inversion parameters of each individual in the target population; obtains a first root mean square value corresponding to each individual in the target population based on the first seafloor topography data and the seismic depth matrix of the area to be inverted; uses the first root mean square value as the target root mean square value; obtains the minimum root mean square value among the target root mean square values ​​corresponding to all individuals in the target population, and sets random parameters based on the minimum root mean square value and the population iteration number; obtains individuals corresponding to the target root mean square value of each stage range from the target population and mixes them to obtain a second number of crossover individuals; the crossover individuals include two individuals; based on a preset crossover ratio, performs a weighted crossover operation on the crossover individuals to obtain a first child individual; obtains a set of individuals to be mutated from the target population based on probability, and performs a crossover operation on each individual in the set of individuals based on a preset mutation random number. A mutation operation is performed to obtain a corresponding second sub-individual; a second population is obtained according to all first sub-individuals, all second sub-individuals and a target population; a second seafloor topographic data of the area to be inverted is obtained based on the inversion parameters corresponding to each individual in the second population; a second root mean square value corresponding to each individual in the second population is obtained based on the second seafloor topographic data and the seismic depth matrix; when there is a second root mean square value in the second population that is less than or equal to the iteration optimal threshold, the corresponding individual is used as the target individual; otherwise, a third number of individuals are selected from the second population based on probability to obtain a third population, the third population is used as the target population, the second root mean square value is used as the target root mean square value, the number of population iterations is increased by 1, and the step of obtaining the minimum root mean square value among the target root mean square values ​​corresponding to all individuals in the target population is returned to execute until the target individual is obtained, or the number of population iterations is equal to the preset maximum number of population iterations; when the number of population iterations is equal to the maximum number of population iterations, the target individual is output according to the target population obtained in the last cycle; the second seafloor topographic data corresponding to the target individual is used as the seafloor inversion result of the area to be inverted. The embodiment of the present invention is based on binary coding combined with relevant genetic operations. Specifically, the binary encoding and decoding is simple, and operations such as crossover and mutation are easy to implement, which can ensure that the improved genetic algorithm search process is more efficient and improve the accuracy and efficiency of data solution. In addition, the embodiment of the present invention first continuously optimizes the population and its corresponding parameters through cyclic iterations based on genetic operations, which can effectively improve the accuracy of seabed inversion, and in the process of cyclic iterations, continuously sets random parameters according to the minimum root mean square value of each round, and then feeds back and applies them to the processing of relevant genetic operations to further optimize the iteration accuracy. The embodiment of the present invention can accurately realize seabed inversion. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0076] Figure 1 A schematic diagram of an implementation environment for performing seafloor inversion based on genetic clonal selection provided by an embodiment of the present invention;

[0077] Figure 2 A schematic flow chart of a seafloor inversion method based on genetic clonal selection provided by an embodiment of the present invention;

[0078] Figure 3 A schematic diagram of the expansion process of obtaining cross-individuals provided in an embodiment of the present invention;

[0079] Figure 4 A schematic diagram of the expansion process of the crossover operation provided by an embodiment of the present invention;

[0080] Figure 5 A schematic diagram of a process of obtaining a set of individuals to be mutated provided in an embodiment of the present invention;

[0081] Figure 6 A schematic diagram of the expansion process of the mutation operation provided by an embodiment of the present invention;

[0082] Figure 7 A schematic diagram of a process of organizing a third population according to an embodiment of the present invention;

[0083] Figure 8 A schematic diagram of the overall process of the seafloor inversion method based on genetic clonal selection provided by an embodiment of the present invention;

[0084] Fig. 9 A schematic diagram of the structure of a seafloor inversion device based on genetic cloning selection provided by an embodiment of the present invention;

[0085] Fig.10 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0086] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0087] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100", "second / S200", etc. in the specification, claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0088] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0089] It is understandable that the seafloor inversion method based on genetic clonal selection provided in the embodiment of the present invention can be applied to any computer device with data processing and computing capabilities, and this computer device can be various types of terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the terminal is a smart phone, tablet computer, laptop computer, desktop computer, etc., but is not limited to this.

[0090] To facilitate the understanding of the technical solution of the present invention, the specific terms of the technical features that may appear in the embodiments of the present invention are first explained:

[0091] Seabed topography: the solid earth surface under water. Due to the cover of seawater, the ups and downs of the seabed topography are difficult to observe directly. The early plumb-bob sounding method was time-consuming and of low precision. Since the 1920s, ships have used echo sounders during navigation, which can quickly measure the depth of the seabed and reveal the truth of the seabed topography in combination with precise positioning. In the present invention, the seabed topography refers to the depth of seawater at various latitudes and longitudes of the ocean.

[0092] Heuristic search is also called informed search. It uses the heuristic information of the problem to guide the search, so as to reduce the search scope and reduce the complexity of the problem. This search process using heuristic information is called heuristic search. For example, genetic algorithm is a classic heuristic search algorithm.

[0093] Genetic Algorithm (GA) is a computational model that simulates the biological evolution process, using mechanisms such as natural selection and gene recombination to search and optimize complex problems. It is a heuristic search algorithm, and its basic idea is to create a group of artificial individuals for optimization and solution by simulating the mechanisms of natural inheritance and evolution. In a genetic algorithm, each individual represents a potential solution, and each individual has its own fitness evaluation criteria. By selecting, crossing over, and mutating these individuals, the adaptability of the current population is gradually improved and the potential solution space is explored in order to find the optimal solution. Genetic algorithms have the characteristics of a wide range of applications, strong global search, and easy parallel computing. They are suitable for optimizing and solving various types of problems, including combinatorial optimization, continuous optimization, and multi-objective optimization. Compared with other algorithms, genetic algorithms can efficiently search for the global optimal solution and are widely used in various fields, including but not limited to engineering optimization design, artificial intelligence tasks, financial analysis and prediction, etc.

[0094] The Parker-Oldenburg inversion method is a frequency domain density interface iterative inversion method proposed by Oldenburg based on the Parker formula. Since this method has the advantage of fast calculation, its application has been rapidly developed. However, there is a downward extension factor in the formula, which causes the formula to have an oscillation phenomenon of high-frequency signals during the inversion iteration process, and as the inversion depth increases, this phenomenon becomes more obvious, which seriously affects the convergence of the inversion result. To solve this problem, a low-pass filter is usually applied in the inversion process to eliminate the high-frequency oscillation phenomenon. The Parker-Oldenburg inversion method is one of the important methods for calculating the seabed topography, and is also the starting point of the core of the present invention. At present, the input parameters of the method (filter-related parameters, density difference, depth), etc. are designed according to constants based on experience, but in fact, there is still room for tuning and mining these parameters.

[0095] RMS: The abbreviation of Root Mean Square. The result of taking the square root of the sum of the squares of N items divided by N is the root mean square result.

[0096] like Figure 1 FIG. 1 is a schematic diagram of an implementation environment provided by an embodiment of the invention. Figure 1The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected to a network wirelessly or wired to complete data transmission and exchange.

[0097] Server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0098] In addition, the server 101 can also be a node server in the blockchain network. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0099] The terminal 102 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal 102 and the server 101 may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present invention.

[0100] Based on the example Figure 1 In the implementation environment shown, an embodiment of the present invention provides a seabed inversion method based on genetic clone selection. The following is explained using the application of the seabed inversion method based on genetic clone selection in the server 101 as an example. It can be understood that the seabed inversion method based on genetic clone selection can also be applied to the terminal 102.

[0101] Reference Figure 2 , Figure 2 The flowchart of the seabed inversion method based on genetic clonal selection applied to a server provided in an embodiment of the present invention, the execution subject of the seabed inversion method based on genetic clonal selection can be any of the aforementioned computer devices (including servers or terminals). Figure 2 , the method comprises the following steps:

[0102] S100, randomly generating a first number of inversion parameters within a first interval, and obtaining a first population based on the inversion parameters initialization; using the first population as a target population; and initializing the population iteration number to 1;

[0103] First, it should be noted that the present invention may also include a data preparation step to initialize various variables, parameters and thresholds that may be applied. Specifically, the parameters that may be involved in the present invention are explained below:

[0104] The parameters mainly include two parts: the parameters of the improved genetic algorithm and the parameters of the Parker-Oldenburg inversion method, etc.

[0105] There are a total of 2 variables searched by the improved genetic algorithm, namely contrast (the physical meaning is: density difference, unit g / cm 3 ), and depth (the physical meaning is depth, unit km). Then, the parameters of the improved genetic algorithm are respectively:

[0106] The maximum density difference maxContrast: the maximum value of contrast, which is determined by the average value of the target search area, generally obtained according to experience, and satisfies minContrast < maxContrast. In most cases, it is sufficient to satisfy maxContrast - minContrast >= 0.4, and it can be set according to the actual situation.

[0107] The minimum density difference minContrast: the minimum value of contrast, which is determined by the average value of the target search area, generally obtained according to experience, and satisfies minContrast < maxContrast. In most cases, it is sufficient to satisfy maxContrast - minContrast >= 0.4, and it can be set according to the actual situation.

[0108] The maximum depth maxDepth: the maximum value of depth, which is determined by the average value of the target search area, generally obtained according to experience, and satisfies maxDepth < minDepth. In most cases, it is sufficient to satisfy maxDepth - minDepth >= 10, and it can be set according to the actual situation.

[0109] The minimum depth minDepth: the minimum value of depth, which is determined by the average value of the target search area, generally obtained according to experience, and satisfies maxDepth < minDepth. In most cases, it is sufficient to satisfy maxDepth - minDepth >= 10, and it can be set according to the actual situation.

[0110] The number of individuals in the population sizePop, the individual scale of the genetic algorithm, is taken according to requirements, and the default is 100.

[0111] The maximum number of iterations of the population maxGenCnt, the number of times the population of the genetic algorithm reproduces, that is, the number of iterations of the genetic algorithm, is taken according to requirements, and the default is 200.

[0112] The probability adjustment factor F1: dynamically adjusts sigma, and the value range is (0, 1], and the default value is 0.5.

[0113] The maximum number of crossover individuals maxCorssNum: controls the maximum number of crossover individuals. The value should not be less than 3. The default value is 30, which means that each population has 30 crossover behaviors.

[0114] Crossover operator ratio crossoverAlpha, a parameter used by the crossover operator, with a value range of [0,1]. The value is determined according to requirements and the default value is 0.5.

[0115] Population adjustment factor F2: The adjustment factor for dynamically controlling the population size, with a value range of (0,1] and a default value of 0.5.

[0116] Iterate the optimal threshold minIterDelt. If an individual less than or equal to minIterDelt is found, it means that the optimal solution is found and the entire search process ends directly.

[0117] The main parameters of the Parker-Oldenburg inversion method are as follows:

[0118] Density difference contrast, unit: g / cm 3 , which is one of the variables searched by means of the improved genetic algorithm, that is, the variable is obtained by searching the improved genetic algorithm and is one of the two search directions mentioned in the present invention.

[0119] Depth depth: unit is km, this is one of the variables searched by means of the improved genetic algorithm, that is, the variable is obtained by searching the improved genetic algorithm, and is one of the two search directions mentioned in the present invention.

[0120] Gravity outlier matrix GravityMat: It is a matrix composed of (longitude, latitude, gravity outlier) triplets, generally data observed by seismic measurement, satellite measurement or other means, and is a constant in the present invention.

[0121] Seismic depth matrix SemisMat: It is a matrix composed of (longitude, latitude, depth) triplets, generally data observed by seismic measurement, satellite measurement or other means, and is a constant in the present invention.

[0122] The iteration threshold criterio, i.e., the iteration rms threshold of the Parker-Oldenburg inversion method, is generally a constant, and the default value is 0.1, which is a constant in the present invention.

[0123] Frequency threshold WH: low-pass filter threshold, the initial value is obtained based on experience, the default value is 0.1, and it is a constant in the present invention.

[0124] Frequency threshold SH: high-pass filter threshold, the initial value is obtained based on experience, the default value is 0.12, and it is a constant in the present invention.

[0125] Window function threshold truncation: It is a signal sampling weighting function in signal processing. The initial value is obtained based on experience, and the default value is 0.1. It is a constant in the present invention.

[0126] Wherein, the inversion parameters correspond to individuals in the target population; the inversion parameters include density difference and seafloor depth; the first interval includes a density difference interval (determined based on a preset maximum density difference value and a minimum density difference value) and a seafloor depth interval (determined based on a preset maximum depth value and a minimum depth value);

[0127] For example, in some specific implementations, initializing the population may be implemented as follows:

[0128] The population is composed of a large number of individuals, each of which has two genes, representing the density difference contrast and the average depth of the seabed depth. The core of population initialization is to generate sizePop individuals and initialize the corresponding genes for each individual. This paper uses the method of randomly generating contrast and depth in the search interval to complete the initialization of individuals. The corresponding generation method is as follows:

[0129] contrast=minContrast+(maxContrast-minContrast)*random();

[0130] depth=minDepth+(maxDepth-minDepth)*random();

[0131] random() means generating random values ​​in [0,1]; normal(0,1) means a normal distribution with a mean of 0 and a standard deviation of 1. The obtained random numbers satisfy the normal distribution, thus ensuring the fairness of gene generation.

[0132] S200, inverting the inversion parameters of each individual in the target population to obtain first seafloor topographic data of the area to be inverted; processing the first seafloor topographic data and the seismic depth matrix of the area to be inverted to obtain a first root mean square value corresponding to each individual in the target population; and using the first root mean square value as the target root mean square value;

[0133] For example, in some specific implementations, after the initialization of the individual is completed, the gene contrast and depth of each individual are traversed one by one, and then the corresponding seafloor topography data is calculated based on the Parker-Oldenburg inversion method. At this time, each individual in the population has calculated the corresponding seafloor topography data, and then combined with the seismic depth matrix SemisMat, the corresponding RMS is calculated, and each individual will calculate its own RMS.

[0134] S300, obtaining the minimum root mean square value among the target root mean square values ​​corresponding to all individuals in the target population, and setting random parameters based on the minimum root mean square value and the number of population iterations;

[0135] It should be noted that, in some embodiments, setting random parameters based on the minimum root mean square value and the number of population iterations may include the following steps: obtaining random parameters based on the number of population iterations and the minimum root mean square value in combination with preset genetic parameter settings; wherein the genetic parameters include an optimal iteration threshold, a maximum number of population iterations, and a probability adjustment factor; the expression of the random parameters is:

[0136]

[0137] Wherein, sigma represents the random parameter; minIterDelt represents the iterative optimal threshold; e represents the natural constant; iter represents the number of population iterations; maxGenCnt represents the maximum number of population iterations; F1 represents the probability adjustment factor; curMinRMS represents the minimum RMS value among the target RMS values.

[0138] For example, in some specific implementations, the calculation formula of Sigma (i.e., sigma / random parameter) is as follows:

[0139]

[0140] Where iter represents the number of iterations of the iterth population, the initial value is 1, the maximum is maxGenCnt, and curMinRMS represents the minimum RMS in the current population. In step 2, during the population initialization process, the RMS of each individual is calculated, and the population is traversed to find the individual with the minimum RMS. The corresponding RMS is curMinRMS.

[0141] S400, obtaining individuals corresponding to the target root mean square value of each stage range from the target population and mixing them to obtain a second number of crossover individuals;

[0142] Among them, the crossover individual includes two individuals;

[0143] It should be noted that in some embodiments, Figure 3As shown, step S400 may include the following steps: S401, traverse the target root mean square values ​​of all individuals in the target population, sort all individuals of the target population from small to large according to the target root mean square values, and obtain a first sequence population; S402, divide all individuals of the first sequence population equally based on the arrangement order to obtain multiple individual groups, and determine all pairing situations of any two individual groups; S403, obtain crossover individuals corresponding to the number of groups from each pairing situation; wherein the number of groups is determined based on the ratio of the second number to the total number of pairing situations, and the two individuals of the crossover individual are respectively taken from the two individual groups of the corresponding pairing situation.

[0144] For example, in some specific implementations, selecting a set of individuals to be crossed by traversing the population can be implemented as follows:

[0145] Sort all individuals from small to large RMS (sort from high to low according to the excellence of individual performance). Take the three groups of individuals as an example, the three groups are divided equally into minRMS, middleRMS, and maxRMS, where minRMS is the best performing group and maxRMS is the worst performing group. The crossover is divided into the following situations:

[0146] 1) minRMS+middleRMS: select the best and worst individuals for crossover.

[0147] 2)minRMS+maxRMS: adjust the best and average individuals for crossover.

[0148] 3) middleRMS+maxRMS: adjust the worst and average individuals for crossover.

[0149] 4)minRMS+minRMS: select the best internal crossover.

[0150] In the face of the above four groups of situations, the number of crossover individuals selected in each group is Here is a brief explanation. Take the first group as an example. Assuming maxCrossNum is 40, the first group needs to select 10 crossover individuals, randomly select an individual from minRMS, and then randomly select an individual from middleRMS to form a crossover individual, and repeat this 10 times. These four groups together make maxCrossNum crossover individuals.

[0151] S500, performing a weighted crossover operation on the crossover individual based on a preset crossover ratio to obtain a first sub-individual;

[0152] It should be noted that the crossover individual includes the first individual and the second individual; in some embodiments, such as Figure 4As shown, step S500 may include the following steps: S501, based on the random parameter, combined with the preset crossover operator ratio setting, a crossover ratio is obtained; wherein the expression of the crossover ratio is:

[0153] β=crossoverAlpha+normal(0,sigma);

[0154] In the formula, β represents the crossover operator; crossoverAlpha represents the crossover operator ratio; crossoverAlpha is a constant; sigma represents a random parameter; normal(0,sigma) means that 0 is the mean and sigma is a random value of the standard deviation;

[0155] S502, based on the crossover ratio, weighted addition is performed on the inversion parameters corresponding to the first individual and the second individual to obtain the inversion parameters of the first sub-individual; wherein the inversion parameters of the first sub-individual are expressed as:

[0156] A3=A1*β+A2*(1-β);

[0157] Where A3 represents the inversion parameters of the first sub-individual; A1 represents the inversion parameters of the first individual; A2 represents the inversion parameters of the second individual.

[0158] For example, in some specific implementations, a crossover operator may be applied to individuals based on probability to select individuals of the next generation, which may be implemented as follows:

[0159] At this step, maxCrossNum crossover individuals have been selected, and each crossover individual is traversed to complete the crossover operation, as follows.

[0160] First, the crossover ratio β is calculated dynamically, and the formula is as follows, where normal(0,sigma) means 0 is the mean, sigma is the random value of the standard deviation; crossoverAlpha represents the crossover operator ratio.

[0161] β=crossoverAlpha+normal(0,sigma);

[0162] Then, the crossover operation is performed for density difference and depth. Assuming that individuals A1 and A2 are crossed, the formula is as follows, where A1 contrast 、A1 depth Respectively represent the density difference and depth of individual A1, A2 contrast 、A2 depth Represent the density difference and depth of individual A2 respectively. A3 contrast 、A3 depthThey respectively represent the density difference and degree of individual A3 obtained by crossover, where the superscripts After and Before are used to indicate the parameter states before and after crossover.

[0163]

[0164] S600, obtaining a set of individuals to be mutated from a target population based on probability, performing a mutation operation on each individual in the set of individuals based on a preset mutation random number, and obtaining a corresponding second child individual;

[0165] It should be noted that in some embodiments, Figure 5 As shown, obtaining a set of individuals to be mutated from a target population based on probability may include the following steps: S601, traversing each individual in the target population, and sequentially setting the mutation probability of each individual based on the target root mean square value combined with the random parameter; wherein the expression of the mutation probability is:

[0166]

[0167] In the formula, prob represents the probability of mutation; sigma represents the random parameter; RMS represents the target root mean square value of the corresponding individual;

[0168] S602, taking the first individual of the target population as the individual to be mutated;

[0169] S603, generating a random number in the second interval as a mutation parameter;

[0170] S604. When the mutation parameter is less than the mutation probability corresponding to the individual to be mutated, the individual to be mutated is sorted into an individual set; otherwise, the next individual of the individual to be mutated in the target population is used as the individual to be mutated, and the process returns to the step of generating a random number as the mutation parameter within the second interval until all individuals in the target population are traversed and the individual set is output.

[0171] For example, in some specific implementations, the set of individuals to be mutated may be selected by traversing the population, which may be specifically implemented as follows:

[0172] Traverse each individual in the population (excluding newly generated offspring individuals) and determine whether they need to be mutated one by one, as follows:

[0173] For each individual, the mutation probability prob is calculated as follows: RMS is the root mean square of the current individual. The larger the RMS, the worse the individual performance and the greater the mutation probability, and vice versa.

[0174] -1*sigma

[0175] prob = e RMS ;

[0176] Then calculate the random number R1 in [0,1]. If R1 is less than prob, the individual participates in the mutation, otherwise it does not participate in the mutation.

[0177] In general, individuals with larger RMS have a greater probability of mutation and a higher probability of participating in mutation. Individuals with smaller RMS have a lower probability of mutation and a lower probability of participating in mutation. This is done to allow individuals with poor performance to participate in the next generation of population reproduction through the opportunity of mutation.

[0178] By traversing the individuals of the population one by one, we finally get the set of individuals to be mutated.

[0179] Among them, in some embodiments, such as Figure 6 As shown, performing a mutation operation on each individual in the individual set based on a preset mutation random number to obtain a corresponding second sub-individual may include the following steps: S605, taking the first individual in the individual set as a mutation individual; S606, generating a mutation random number with 0 as the mean and a random parameter as the standard deviation; S607, performing mutation assignment on the inversion parameter corresponding to the mutation individual based on the product of the difference between the mutation random number and the interval range of the first interval to obtain the inversion parameter of the second sub-individual; wherein the expression of the inversion parameter of the second sub-individual is:

[0180] A4=A1+(max-mix)*normal(0,sigma);

[0181] Where A4 represents the inversion parameter of the second sub-individual; A1 represents the inversion parameter of the mutant individual; max represents the maximum value of the first interval; min represents the minimum value of the first interval; normal(0, sigma) represents the mutant random number.

[0182] For example, in some specific implementations, a mutation operator may be applied to individuals based on probability to select individuals for the next generation, which may be implemented as follows:

[0183] At this point, several individuals to be mutated have been selected, and the individuals have been traversed to complete the mutation operation. Assuming that individual A1 is mutated, the formula is as follows A1 contrast 、A1 depth Represent the density difference and depth of individual A1 respectively. A4 contrast 、A4 depth They represent the density difference and degree of the individual A4 obtained by mutation. Normal(0,sigma) means that 0 is the mean and sigma is the random value of the standard deviation.

[0184] A4 contrast =A1 contrast+(maxContrast-minContrast)*normal(0,sigma);

[0185] A4 depth =A1 depth +(maxContrast-minContrast)*normal(0,sigma);

[0186] S700, obtaining a second population according to all first sub-individuals, all second sub-individuals and the target population; obtaining second seafloor topographic data of the area to be inverted based on the inversion parameters corresponding to each individual in the second population; obtaining a second root mean square value corresponding to each individual in the second population based on the second seafloor topographic data and seismic depth matrix processing;

[0187] Exemplarily, in some specific implementations, first, the seabed topography is calculated based on the current population: at this time, the individuals that make up the population are composed of parent individuals and child individuals, the parent individuals are individuals participating in crossover mutation, and the child individuals are new individuals obtained through crossover and mutation. The gene contrast and depth of all child individuals are traversed, and then the corresponding seabed topography data are calculated based on the Parker-Oldenburg inversion method. Then, the fitness function value of each individual is evaluated: at this time, the seabed topography data of all child individuals are traversed, and then combined with the seismic depth matrix SemisMat, the corresponding RMS is calculated, and each individual will calculate its own RMS. At this point, the RMS of all individuals (parent individuals and child individuals) has been calculated.

[0188] S800, when there is a second RMS value in the second population that is less than or equal to the iterative optimal threshold, the corresponding individual is taken as the target individual, and the process jumps to step S1100; otherwise, the process executes the subsequent steps;

[0189] Exemplarily, in some specific implementations, all individuals in the population are traversed to determine whether there is an RMS less than the iterative optimal threshold minIterDelt. If so, go to step S1100, indicating that the optimal individual (optimal solution) has been found, otherwise execute subsequent steps.

[0190] S900, based on probability, selecting a third number of individuals from the second population to obtain a third population, taking the third population as the target population, taking the second RMS value as the target RMS value, increasing the number of population iterations by 1, and returning to execute the step of obtaining the minimum RMS value among the target RMS values ​​corresponding to all individuals in the target population, until the target individual is obtained, or the number of population iterations is equal to the preset maximum number of population iterations;

[0191] It should be noted that in some embodiments, Figure 7As shown, selecting a third number of individuals from the second population based on probability to obtain a third population may include the following steps: S901, obtaining the population size of the second population; S902, obtaining a third number based on a random parameter and the population size in combination with a preset population size adjustment factor; wherein the expression of the third number is:

[0192] newSizePop=max(curPopSize*F2,curPopSize+F2*curPopSize*normal(0,sigma));

[0193] Wherein, newSizePop represents the third quantity; curPopSize represents the population size; F2 represents the population size adjustment factor; sigma represents a random parameter; normal(0,sigma) represents a random value with 0 as the mean and sigma as the standard deviation; max(X,Y) represents the maximum value of X and Y;

[0194] S903, traverse the second root mean square values ​​of all individuals in the second population, sort all individuals in the second population according to the second root mean square values ​​from small to large, and obtain a second sequence population; S904, select a fourth number of individuals from the preamble of the second sequence population as the first candidate individual set; the fourth number is half of the third number; S905, randomly select a fourth number of individuals from the other individuals in the second sequence population except the first candidate individual set as the second candidate individual set; S906, obtain the third population according to the first candidate individual set and the second candidate individual set.

[0195] For example, in some specific implementations, the selection operator may be applied to individuals based on probability, which may be implemented as follows:

[0196] The new population size is calculated based on probability. The calculation formula is as follows, where curPopSize represents the current population size (the number of parent and child individuals), newPopSize represents the number of individuals after selection, and normal(0,sigma) represents a random value with 0 as the mean and sigma as the standard deviation. curPopSize has a guaranteed value, which is at least curPopSize*F2.

[0197] newSizePop=max(curPopSize*F2,curPopSize+F2*curPopSize*normal(0,sigma)) After completing the calculation of newPopSize, you can start to eliminate redundant individuals and sort all individuals from small to large according to RMS. Individuals directly enter the next generation population. Individuals, randomly selected based on probability Finally, the selection of newPopSize individuals is completed to form the next generation group.

[0198] To summarize, the core idea of ​​the selection operator is that the top 50% of the best individuals are directly selected as the next generation of the population, and the rest of the individuals are selected based on probability. As the population reproduces, the best individuals gradually gather, and the probability-based selection will also retain individuals with good potential.

[0199] It should be noted that after the operation of step S300 to step S900, it means that a population reproduction is completed and a new population is obtained, but no individuals that meet the expectations are found and need to participate in the next round of population reproduction. Steps S300 to step S900 are executed in a loop, and each execution indicates that the population reproduction is iterated once until the maximum number of population iterations maxGenCnt is reached.

[0200] S1000, when the number of population iterations is equal to the maximum number of population iterations, the target individual is output according to the target population obtained in the last cycle;

[0201] In some embodiments, outputting a target individual according to the target population obtained in the last cycle may include the following steps: obtaining the minimum root mean square value among the target root mean square values ​​corresponding to all individuals in the target population obtained in the last cycle, and outputting the individual corresponding to the minimum root mean square value as the target individual;

[0202] S1100, taking the second seafloor topographic data corresponding to the target individual as the seafloor inversion result of the area to be inverted.

[0203] For example, in some specific implementations, there are only two situations to find the optimal solution (i.e., the target individual): the optimal vector that satisfies the iterative optimal threshold minIterDelt, or the optimal vector obtained by searching the entire space (i.e., the individual with the smallest RMS value in the last population). At this point, the entire search process ends, and not only the optimal solution is obtained, but also the corresponding seabed topography data.

[0204] In order to explain the principle of the technical solution of the present invention in detail, the overall process of the present invention is described below in combination with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and cannot be regarded as a limitation of the present invention.

[0205] First of all, it should be noted that in the current technical strategy, the parameters of Parker-Oldenburg inversion are regarded as constant values, which limits the accuracy of the solution. In addition, the existing technology also faces several significant defects:

[0206] ① The current method simplifies the relationship between density difference and depth and assumes that they are linear, which leads to the insufficient accuracy of the seabed topography data obtained by Parker-Oldenburg inversion.

[0207] ② When exploring the optimal parameters of the Parker-Oldenburg inversion method, despite extensive testing, the crossover and mutation mechanisms in the existing genetic algorithm performed poorly, as evidenced by slow solution speed and large fluctuations in average accuracy.

[0208] ③ Due to the huge amount of overall calculations and the lack of a unified execution framework, the automation process of terrain inversion faces challenges, which in turn affects the accuracy of the final result, making it appear rougher than the actual situation.

[0209] In view of this, the present invention proposes a method for solving the seabed topography based on an improved genetic algorithm and Parker-Oldenburg inversion based on clonal selection. The improved genetic algorithm is used to find the optimal parameters, and the Parker-Oldenburg inversion method is used to obtain a more accurate seabed topography. Figure 8 As shown, the present invention may include the following process steps:

[0210] Step 1: Parameter initialization. The parameters mainly include two parts: improved genetic algorithm parameters and Parker-Oldenburg inversion method parameters (for details of the specific parameters, please refer to the above parameter description and will not be repeated here).

[0211] Step 2: Initialize the population. The population is composed of a large number of individuals, each of which has two genes, representing the density difference contrast and the average depth of the seabed depth. The core of population initialization is to generate sizePop individuals and initialize the corresponding genes for each individual. This paper uses the method of randomly generating contrast and depth in the search interval to complete the initialization of individuals. The corresponding generation method is as follows:

[0212] contrast=minContrast+(maxContrast-minContrast)*random();

[0213] depth=minDepth+(maxDepth-minDepth)*random();

[0214] random() represents the random value generated in [0,1]; normal(0,1) represents the normal distribution with a mean of 0 and a standard deviation of 1. The random number obtained satisfies the normal distribution, thereby ensuring the fairness of gene generation. After completing the initialization of the individual, the gene contrast and depth of each individual are traversed one by one, and then the corresponding seafloor topography data is calculated based on the Parker-Oldenburg inversion method. At this point, each individual in the population has calculated the corresponding seafloor topography data, and then combined with the seismic depth matrix SemisMat, the corresponding RMS is calculated. Each individual will calculate its own RMS and go to step 3.

[0215] Step 3: Update the Sigma value. The calculation formula of Sigma (i.e. sigma / random parameter) is as follows:

[0216]

[0217] Where iter represents the number of iterations of the iterth population, the initial value is 1, the maximum is maxGenCnt, and curMinRMS represents the minimum RMS in the current population. In step 2, during the population initialization process, the RMS of each individual is calculated, and the population is traversed to find the individual with the minimum RMS. The corresponding RMS is curMinRMS.

[0218] Step 4: Traverse the population and select the set of individuals to be crossed. Sort all individuals from small to large according to RMS (sort from high to low according to the excellence of individual performance). Take the example of three groups of individuals, divided equally into three groups of minRMS, middleRMS, and maxRMS, where minRMS is the best performing group and maxRMS is the worst performing group. Crossover is divided into the following situations:

[0219] 1) minRMS+middleRMS: select the best and worst individuals for crossover.

[0220] 2)minRMS+maxRMS: adjust the best and average individuals for crossover.

[0221] 3) middleRMS+maxRMS: adjust the worst and average individuals for crossover.

[0222] 4)minRMS+minRMS: select the best internal crossover.

[0223] In the face of the above four groups of situations, the number of crossover individuals selected in each group is Here is a brief explanation. Take the first group as an example. Assuming maxCrossNum is 40, the first group needs to select 10 crossover individuals. Randomly select an individual from minRMS, and then randomly select an individual from middleRMS to form a crossover individual. Repeat this 10 times. These four groups together make maxCrossNum crossover individuals. Go to step 5.

[0224] Step 5: Apply the crossover operator to the individuals based on probability and select the next generation of individuals. At this point, maxCrossNum crossover individuals have been selected, and each crossover individual is traversed to complete the crossover operation, as follows.

[0225] First, the crossover ratio β is calculated dynamically, and the formula is as follows, where normal(0,sigma) means 0 is the mean, sigma is the random value of the standard deviation; crossoverAlpha represents the crossover operator ratio.

[0226] β=crossoverAlpha+normal(0,sigma);

[0227] Then, the crossover operation is performed for density difference and depth. Assuming that individuals A1 and A2 are crossed, the formula is as follows, where A1 contrast 、A1 depth Respectively represent the density difference and depth of individual A1, A2 contrast 、A2 depth Represent the density difference and depth of individual A2 respectively. A3 contrast 、A3 depth They respectively represent the density difference and degree of individual A3 obtained by crossover, where the superscripts After and Before are used to indicate the parameter states before and after crossover.

[0228]

[0229] Here is a specific example. Taking the intersection of A1 and A2 as an example, assuming that the density difference of individual A1 is A1 contrast =0.5, the depth of individual A1 is A1 depth =20; the density difference of individual A2 is A2 contrast =0.3, depth A2 of individual A2 depth =10, and β is 0.8, then the individual A3 is calculated by the formula

[0230] A3 contrast =0.5*0.8+(1-0.8)*0.3=0.46

[0231] A3 depth =20*0.8+(1-0.8)*10=18

[0232] In general, through the crossover operations in steps 4 and 5, maxCrossNum offspring individuals are obtained. Go to step 6.

[0233] Step 6: Traverse the population and select the set of individuals to be mutated. Traverse each individual in the population (excluding newly generated offspring individuals) and determine whether they need to be mutated one by one, as follows:

[0234] For each individual, the mutation probability prob is calculated as follows: RMS is the root mean square of the current individual. The larger the RMS, the worse the individual performance and the greater the mutation probability, and vice versa.

[0235]

[0236] Then calculate the random number R1 in [0,1]. If R1 is less than prob, the individual participates in the mutation, otherwise it does not participate in the mutation.

[0237] In general, individuals with larger RMS have a greater probability of mutation and a higher probability of participating in mutation. Individuals with smaller RMS have a lower probability of mutation and a lower probability of participating in mutation. This is done to allow individuals with poor performance to participate in the next generation of population reproduction through the opportunity of mutation.

[0238] Traverse the individuals in the population one by one, and finally obtain the set of individuals to be mutated, and go to step 7.

[0239] Step 7: Apply the mutation operator to individuals based on probability and select the next generation of individuals. At this point, several individuals to be mutated have been selected, and the individuals have been traversed to complete the mutation operation. Assume that individual A1 is mutated, the formula is as follows A1 contrast 、A1 depth Represent the density difference and depth of individual A1 respectively. A4 contrast 、A4 depth They represent the density difference and degree of the individual A4 obtained by mutation. Where normal(0,sigma) means 0 is the mean and sigma is the random value of the standard deviation.

[0240] A4 contrast =A1 contrast +(maxContrast-minContrast)*normal(0,sigma);

[0241] A4 depth =A1 depth +(maxContrast-minContrast)*normal(0,sigma);

[0242] In general, through the mutation operations of step 6 and step 7, several offspring individuals are obtained. Go to step 8.

[0243] Step 8: Calculate the seafloor topography based on the current population. At this time, the individuals that make up the population are composed of parent individuals and offspring individuals. Parent individuals are individuals that participate in crossover mutation, and offspring individuals are new individuals obtained through crossover and mutation. Traverse the gene contrast and depth of all offspring individuals, and then calculate the corresponding seafloor topography data based on the Parker-Oldenburg inversion method. Go to step 9.

[0244] Step 9: Evaluate the fitness function value of each individual. At this point, traverse the seafloor topography data of all child individuals, and then combine the seismic depth matrix SemisMat to calculate the corresponding RMS. Each individual will calculate its own RMS. At this point, the RMS of all individuals (parent individuals and child individuals) has been calculated, and go to step 10.

[0245] Step 10: There are individuals with RMS less than the threshold. Traverse all individuals in the population and determine whether there is an individual with RMS less than the iterative optimal threshold minIterDelt. If so, go to step 14, indicating that the optimal individual (optimal solution) has been found. Otherwise, go to step 11.

[0246] Step 11: Apply the selection operator to individuals based on probability. Calculate the new population size based on probability, the calculation formula is as follows, where curPopSize represents the current population size (the number of parent and child individuals), newPopSize represents the number of individuals after selection, and normal(0,sigma) represents a random value with 0 as the mean and sigma as the standard deviation. curPopSize has a guaranteed value, at least curPopSize*F2.

[0247] newSizePop=max(curPopSize*F2,curPopSize+F2*curPopSize*normal(0,sigma)) After completing the calculation of newPopSize, you can start to eliminate redundant individuals and sort all individuals from small to large according to RMS. Individuals directly enter the next generation population. Individuals, randomly selected based on probability Finally, the selection of newPopSize individuals is completed to form the next generation group.

[0248] To summarize, the core idea of ​​the selection operator is that the top 50% of the best individuals are directly selected as the next generation of the population, and the rest of the individuals are selected based on probability. As the population reproduces, the best individuals gradually gather, and the probability-based selection will also retain individuals with good potential.

[0249] Step 12: Get the next generation population. After the operations from step 3 to step 11, it means that a population reproduction is completed and a new population is obtained, but the expected individuals are still not found and need to participate in the next round of population reproduction. Go to step 13.

[0250] Step 13: Satisfy the maximum number of population iterations. Steps 3 to 12 are executed in a loop. Each execution indicates that the population reproduces once, until the maximum number of population iterations maxGenCnt is reached. If it is not exceeded, go to step 3, otherwise go to step 14.

[0251] Step 14: Find the optimal solution. This step yields the optimal solution for the entire search process. There are only two solutions: the optimal vector that satisfies the iterative optimal threshold minIterDelt, or the optimal vector obtained by searching the entire space. At this point, the entire search process ends, and not only the optimal solution is obtained, but also the corresponding seafloor topography data.

[0252] In summary, the present invention proposes a method for solving seafloor topography based on an improved genetic algorithm and Parker-Oldenburg inversion based on clonal selection, which finds the optimal parameters through a genetic algorithm based on an improved operator, and with the help of the Parker-Oldenburg inversion method, obtains a more accurate seafloor topography. Compared with the prior art, the present invention has at least the following beneficial effects:

[0253] 1) An improved genetic algorithm process based on clonal selection is proposed, which optimizes the calculation process of genetic operators, gives priority to selection and mutation operators, and then selects operators to ensure that each individual attempts evolution in different directions, improves the diversity of gene expression of individuals in the population, and improves the search efficiency of the genetic algorithm.

[0254] 2) The optimized crossover, mutation and selection operators are proposed to improve the computational complexity of the genetic algorithm, ensure that the improved genetic algorithm search process is more efficient, and improve the accuracy and efficiency of data solution;

[0255] 3) The improved genetic algorithm based on clonal selection and Parker-Oldenburg inversion are combined to ensure the accuracy of the seabed topography and improve the computational efficiency.

[0256] It should be emphasized that the present invention proposes searching for the optimal density difference contrast and depth based on an improved genetic algorithm, and combining it with the Parker-Oldenburg inversion method to solve a more accurate seabed topography.

[0257] On the other hand, Fig. 9 As shown, the embodiment of the present invention provides a seafloor inversion device 900 based on genetic cloning selection, which may include:

[0258] The first module 901 is used to randomly generate a first number of inversion parameters in a first interval, and obtain a first population based on the inversion parameters initialization; the first population is used as a target population; the number of population iterations is initialized to 1; wherein the inversion parameters correspond to individuals in the target population; the inversion parameters include density difference and seafloor depth;

[0259] The second module 902 is used to obtain first seafloor topographic data of the area to be inverted based on the inversion parameters of each individual in the target population; obtain a first root mean square value corresponding to each individual in the target population based on the first seafloor topographic data and the seismic depth matrix of the area to be inverted; and use the first root mean square value as the target root mean square value;

[0260] The third module 903 is used to obtain the minimum root mean square value among the target root mean square values ​​corresponding to all individuals in the target population, and set random parameters based on the minimum root mean square value and the number of population iterations;

[0261] The fourth module 904 is used to obtain individuals corresponding to the target root mean square value of each stage range from the target population and mix them to obtain a second number of crossover individuals; the crossover individuals include two individuals;

[0262] The fifth module 905 is used to perform a weighted crossover operation on the crossover individual based on a preset crossover ratio to obtain a first sub-individual;

[0263] The sixth module 906 is used to obtain a set of individuals to be mutated from the target population based on probability, and perform a mutation operation on each individual in the set of individuals based on a preset mutation random number to obtain a corresponding second child individual;

[0264] The seventh module 907 is used to obtain a second population according to all the first sub-individuals, all the second sub-individuals and the target population; invert the second seafloor topography data of the area to be inverted based on the inversion parameters corresponding to each individual in the second population; and obtain the second root mean square value corresponding to each individual in the second population based on the second seafloor topography data and the seismic depth matrix processing;

[0265] The eighth module 908 is used to take the corresponding individual as the target individual when there is a second RMS value less than or equal to the iterative optimal threshold in the second population; otherwise,

[0266] The ninth module 909 is used to select a third number of individuals from the second population based on probability to obtain a third population, take the third population as the target population, take the second RMS value as the target RMS value, increase the number of population iterations by 1, and return to execute the third module until the target individual is obtained, or the number of population iterations is equal to the preset maximum number of population iterations;

[0267] The tenth module 910 is used to output a target individual according to the target population obtained in the last cycle when the number of population iterations is equal to the maximum number of population iterations;

[0268] The eleventh module 911 is used to use the second seafloor topographic data corresponding to the target individual as the seafloor inversion result of the area to be inverted.

[0269] The contents of the method embodiments of the present invention are all applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0270] On the other hand, an embodiment of the present invention further provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned hydrate stability region bottom boundary prediction method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0271] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0272] like Fig.10 As shown, Fig.10 The hardware structure of an electronic device 1000 of another embodiment is illustrated. The electronic device 1000 includes:

[0273] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.

[0274] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the network node population optimization method of the embodiment of the present invention;

[0275] Input / output interface 1003, used to implement information input and output;

[0276] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0277] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0278] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0279] The electronic device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0280] The contents of the method embodiments of the present invention are all applicable to the electronic device embodiments. The functions specifically implemented by the electronic device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0281] Another aspect of an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0282] The contents of the method embodiments of the present invention are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0283] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0284] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0285] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A seafloor inversion method based on genetic clonal selection, characterized in that: The following steps are involved: Randomly generate a first number of inversion parameters in a first interval, and obtain a first population based on the inversion parameters; use the first population as a target population; the number of population iterations is 1; wherein the inversion parameters correspond to individuals in the target population; and the inversion parameters include density difference and seafloor depth; Inverting the inversion parameters of each individual in the target population to obtain first seafloor topography data of the area to be inverted; processing the first seafloor topography data and the seismic depth matrix of the area to be inverted to obtain a first root mean square value corresponding to each individual in the target population; and using the first root mean square value as a target root mean square value; Obtaining a minimum root mean square value among the target root mean square values ​​corresponding to all the individuals in the target population, and setting a random parameter based on the minimum root mean square value and the number of population iterations; The individuals corresponding to the target root mean square value of each stage range are obtained from the target population and mixed to obtain a second number of crossover individuals; the crossover individuals include two of the individuals; Based on a preset crossover ratio, a weighted crossover operation is performed on the crossover individual to obtain a first sub-individual; Obtaining a set of individuals to be mutated from the target population based on probability, and performing a mutation operation on each individual in the set of individuals based on a preset mutation random number to obtain a corresponding second child individual; Arrange all the first sub-individuals, all the second sub-individuals and the target population to obtain a second population; invert the second seafloor topographic data of the area to be inverted based on the inversion parameters corresponding to each of the individuals in the second population; and obtain a second root mean square value corresponding to each of the individuals in the second population based on the second seafloor topographic data and the seismic depth matrix; When there is an individual in the second population whose second root mean square value is less than or equal to the iterative optimal threshold, the corresponding individual is taken as the target individual; otherwise, Selecting a third number of the individuals from the second population based on probability to obtain a third population, taking the third population as the target population, taking the second RMS value as the target RMS value, increasing the number of population iterations by 1, and returning to execute the step of obtaining the minimum RMS value among the target RMS values ​​corresponding to all the individuals in the target population, until the target individual is obtained, or the number of population iterations is equal to the preset maximum number of population iterations; When the population iteration number is equal to the population maximum iteration number, outputting the target individual according to the target population obtained in the last cycle; The second seafloor topographic data corresponding to the target individual is used as the seafloor inversion result of the area to be inverted.

2. The seafloor inversion method based on genetic clonal selection according to claim 1, characterized in that: The step of setting random parameters based on the minimum root mean square value and the number of population iterations comprises the following steps: Based on the population iteration number and the minimum root mean square value, the random parameter is obtained in combination with a preset genetic parameter setting; The genetic parameters include the optimal threshold of iteration, the maximum number of iterations of the population and the probability adjustment factor; the expression of the random parameter is: Wherein, sigma represents the random parameter; minIterDelt represents the iterative optimal threshold; e represents the natural constant; iter represents the number of population iterations; maxGenCnt represents the maximum number of population iterations; F1 represents the probability adjustment factor; curMinRMS represents the minimum RMS value among the target RMS values.

3. The seafloor inversion method based on genetic clonal selection according to claim 1, characterized in that: The step of obtaining the individuals corresponding to the target root mean square value of each stage range from the target population and mixing them to obtain a second number of crossover individuals comprises the following steps: Traversing the target root mean square values ​​of all the individuals in the target population, and sorting all the individuals in the target population in ascending order according to the target root mean square values, to obtain a first sequence population; Dividing all the individuals of the first sequence population equally based on the arrangement order to obtain a plurality of individual groups, and determining all pairing situations of any two of the individual groups; Obtain the crossover individuals of the corresponding group number from each pairing situation; The number of the groups is determined based on the ratio of the second number to the total number of the pairing situations, and the two individuals of the crossover individuals are respectively taken from the two individual groups corresponding to the pairing situations.

4. The seafloor inversion method based on genetic clonal selection according to claim 1, characterized in that: The crossover individual includes a first individual and a second individual; and performing a weighted crossover operation on the crossover individual based on a preset crossover ratio to obtain a first sub-individual includes the following steps: Based on the random parameter, the crossover ratio is obtained in combination with a preset crossover operator ratio setting; Wherein, the expression of the crossover ratio is: β=crossoverAlpha+normal(0,sigma); In the formula, β represents the crossover operator; crossoverAlpha represents the crossover operator ratio; crossoverAlpha is a constant; sigma represents a random parameter; normal(0,sigma) means that 0 is the mean and sigma is a random value of the standard deviation; Based on the crossover ratio, weighted addition is performed on the inversion parameters corresponding to the first individual and the second individual to obtain the inversion parameters of the first sub-individual; The expression of the inversion parameter of the first sub-individual is: A3=A1*β+A2*(1-β); Where A3 represents the inversion parameters of the first sub-individual; A1 represents the inversion parameters of the first individual; A2 represents the inversion parameters of the second individual.

5. The seafloor inversion method based on genetic clonal selection according to claim 1, characterized in that: The method of obtaining a set of individuals to be mutated from the target population based on probability comprises the following steps: Traversing each of the individuals in the target population, and sequentially setting the mutation probability of each of the individuals based on the target root mean square value combined with the random parameter; Among them, the expression of the mutation probability is: In the formula, prob represents the probability of mutation; sigma represents the random parameter; RMS represents the target root mean square value of the corresponding individual; Taking the first individual of the target population as the individual to be mutated; Generate a random number in the second interval as a mutation parameter; When the mutation parameter is less than the mutation probability corresponding to the individual to be mutated, the individual to be mutated is sorted into the individual set; otherwise, the next individual of the individual to be mutated in the target population is taken as the individual to be mutated, and the step of generating a random number as the mutation parameter within the second interval is returned to execute until all the individuals in the target population are traversed and the individual set is output.

6. The seafloor inversion method based on genetic clonal selection according to claim 1, characterized in that: The step of performing a mutation operation on each individual in the individual set based on a preset mutation random number to obtain a corresponding second child individual includes the following steps: Taking the first individual in the individual set as a variant individual; Generate the variant random number with 0 as mean and the random parameter as standard deviation; Performing mutation assignment on the inversion parameter corresponding to the mutated individual based on the product of the mutated random number and the interval range difference of the first interval, so as to obtain the inversion parameter of the second sub-individual; The expression of the inversion parameter of the second sub-individual is: A4=A1+(max-mix)*normal(0,sigma); Where A4 represents the inversion parameter of the second sub-individual; A1 represents the inversion parameter of the mutant individual; max represents the maximum value of the first interval; min represents the minimum value of the first interval; normal(0, sigma) represents the mutant random number.

7. The seafloor inversion method based on genetic clonal selection according to claim 1, characterized in that: The step of selecting a third number of individuals from the second population based on probability to obtain a third population comprises the following steps: Obtaining the population size of the second population; Based on the random parameter and the population size, the third size is obtained in combination with a preset population size adjustment factor; Wherein, the expression of the third quantity is: newSizePop=max(curPopSize*F2,curPopSize+F2*curPopSize*normal(0,sigma)); Wherein, newSizePop represents the third quantity; curPopSize represents the population size; F2 represents the population size adjustment factor; sigma represents a random parameter; normal(0,sigma) represents a random value with 0 as the mean and sigma as the standard deviation; max(X,Y) represents the maximum value of X and Y; Traversing the second root mean square values ​​of all the individuals in the second population, and sorting all the individuals in the second population in ascending order according to the second root mean square values, to obtain a second sequence population; Selecting a fourth number of the individuals from the pre-sequence of the second sequence population as a first candidate individual set; the fourth number is half of the third number; Randomly selecting the fourth number of individuals from the individuals other than the first candidate individual set in the second sequence population as a second candidate individual set; The third population is obtained by sorting the first candidate individual set and the second candidate individual set.

8. A seafloor inversion device based on genetic clonal selection, characterized in that: include: A first module is used to randomly generate a first number of inversion parameters in a first interval, and obtain a first population based on the inversion parameters initialization; taking the first population as the target population; The number of iterations of the initialization population is 1; wherein the inversion parameters correspond to individuals in the target population; the inversion parameters include density difference and seafloor depth; The second module is used to obtain first seafloor topographic data of the area to be inverted based on the inversion parameters of each individual in the target population; obtain a first root mean square value corresponding to each individual in the target population based on the first seafloor topographic data and the seismic depth matrix of the area to be inverted; and use the first root mean square value as the target root mean square value; A third module is used to obtain the minimum root mean square value among the target root mean square values ​​corresponding to all the individuals in the target population, and set a random parameter based on the minimum root mean square value and the number of population iterations; A fourth module is used to obtain the individuals corresponding to the target root mean square value of each stage range from the target population and mix them to obtain a second number of crossover individuals; the crossover individuals include two of the individuals; A fifth module is used to perform a weighted crossover operation on the crossover individual based on a preset crossover ratio to obtain a first sub-individual; The sixth module is used to obtain a set of individuals to be mutated from the target population based on probability, and perform a mutation operation on each individual in the set of individuals based on a preset mutation random number to obtain a corresponding second child individual; The seventh module is used to obtain a second population according to all the first sub-individuals, all the second sub-individuals and the target population; obtain the second seabed topographic data of the area to be inverted based on the inversion parameters corresponding to each of the individuals in the second population; obtain the second root mean square value corresponding to each of the individuals in the second population based on the second seabed topographic data and the seismic depth matrix; The eighth module is used to take the corresponding individual as the target individual when the second RMS value in the second population is less than or equal to the iterative optimal threshold; otherwise, A ninth module is used for selecting a third number of the individuals from the second population based on probability to obtain a third population, taking the third population as the target population, taking the second root mean square value as the target root mean square value, increasing the number of population iterations by 1, and returning to execute the third module until the target individual is obtained, or the number of population iterations is equal to a preset maximum number of population iterations; A tenth module is used for outputting the target individual according to the target population obtained in the last cycle when the number of iterations of the population is equal to the maximum number of iterations of the population; An eleventh module is used to use the second seafloor topography data corresponding to the target individual as the seafloor inversion result of the area to be inverted.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images