Genetic intelligent lunar exploration site selection method and device considering detection value index

Abstract

The application relates to a genetic intelligent lunar exploration site selection method and device considering a detection value index, which comprises the following steps: acquiring multiple types of lunar data, and constructing a multi-target index system of lunar landing site selection; based on the multi-target index system, calculating lunar site selection index factors and carrying out pretreatment; based on the pretreated lunar site selection index factors, calculating a scientific value index and an engineering safety index to comprehensively construct a lunar exploration value index model; adopting a genetic intelligent algorithm to obtain optimal site selection parameters of the lunar exploration value index model; and based on the lunar exploration value index model and the optimal site selection parameters, calculating a detection value index, and self-adapting threshold screening to form a high-value detection area. Compared with the prior art, the application has the advantages of screening a high-credibility detection area.

Description

Technical Field

[0001] This invention relates to the field of geographic information, and in particular to a genetically intelligent lunar exploration site selection method and device that takes into account the exploration value index. Background Technology

[0002] For over 60 years, countries and regions around the world have been racing to explore the moon. Some probes have lost contact or become inoperable after landing. Choosing a landing site with high engineering safety is one of the key factors for the success of lunar exploration missions, demonstrating the significant impact of site selection on engineering safety. Furthermore, the optimal landing area needs to possess outstanding scientific value, ensure the safe descent and movement of the probe, and facilitate energy replenishment and data communication. Landing site selection requires a comprehensive consideration of scientific objectives and engineering safety conditions, weighing factors such as scientific value and technical difficulty. Determining possible landing areas and sites is the first problem to be solved in carrying out deep space landing exploration missions and is a prerequisite for the success of the mission.

[0003] Existing site selection methods primarily rely on multi-objective analysis of engineering and scientific site selection evaluation indicators by experts and technicians. The goal is to select candidate landing areas with high scientific value and suitable engineering sampling. However, relying solely on manual prioritization of landing areas makes it difficult to accurately and efficiently establish a unified quantitative evaluation model for site selection. This fails to effectively screen a wide range of highly reliable priority landing and exploration areas, and carries the risk of overlooking potentially high-value scientific research areas and areas with high engineering safety. Furthermore, given the constantly changing indicator requirements during the site selection process, manual site selection suffers from drawbacks such as massive workload, long processing time, and high risk of rework.

[0004] Existing research methods include landing site selection models based on the weight of evidence and fractals, sliding window landing site optimization models, and multi-factor comprehensive site selection models that consider multiple objectives. These methods all focus on specific types of scientific objectives and their spatial distribution, but they suffer from insufficient ability to comprehensively quantify multiple scientific value indicators. Furthermore, existing methods often achieve safe landing site selection by setting empirical thresholds or expert scoring for constraint indicators. With the increasing abundance and quality of lunar exploration remote sensing data, the amount of basic data available for site selection is constantly increasing, making it difficult to achieve comprehensive multi-factor analysis through empirical judgment. Existing methods have the limitation of failing to effectively express and comprehensively consider multiple scientific value and engineering safety indicators. Summary of the Invention

[0005] The purpose of this invention is to provide a genetically intelligent lunar exploration site selection method and equipment that considers the exploration value index to screen highly reliable lunar landing exploration areas.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A genetically-based intelligent lunar exploration site selection method that takes into account the exploration value index includes the following steps:

[0008] Acquire various types of lunar data to construct a multi-objective indicator system for lunar landing site selection;

[0009] Based on the aforementioned multi-objective index system, lunar site selection index factors are calculated and preprocessed.

[0010] Based on the preprocessed lunar site selection index factors, the scientific value index and engineering safety index are calculated to comprehensively construct a lunar exploration value index model.

[0011] The optimal site parameters of the lunar exploration value index model are obtained using a genetic intelligent algorithm.

[0012] Based on the lunar exploration value index model and optimal site selection parameters, the exploration value index is calculated, and high-value exploration areas are selected through adaptive threshold screening.

[0013] Furthermore, the specific steps for calculating and preprocessing the lunar site selection index factors include:

[0014] Calculate the corresponding lunar site selection index factors based on the indicators in the multi-objective index system.

[0015] The spatial reference of the lunar site selection index factors is unified, and coordinate matching is performed among the lunar site selection index factors to unify the data resolution.

[0016] Furthermore, the specific steps for comprehensively constructing the lunar exploration value index model include:

[0017] Based on the requirements of the site selection mission, scientific value index factors are selected from the lunar site selection index factors to form a scientific value index.

[0018] Based on the requirements of the site selection mission, engineering safety index factors are selected from the lunar site selection index factors to form an engineering safety index.

[0019] Based on the aforementioned scientific value index and engineering safety index, a lunar exploration value index model is constructed.

[0020] Furthermore, the expressions for the scientific value index and the engineering safety index are as follows:

[0021]

[0022]

[0023] In the formula, x and y represent the geographical coordinates of the candidate region, and f i(1…n,norm)(x,y) represents n scientific value index factors of the study area, SVI(x,y) represents the scientific value index, and w i The importance of scientific site selection index i is represented; ESI(x,y) represents the engineering safety index, f j (1…m,norm)(x,y) represents the m engineering safety index factors in this region, w j This represents the importance of the engineering safety indicator j.

[0024] Furthermore, the detection value index model is as follows:

[0025]

[0026] In the formula, EVI represents the lunar exploration value index, C represents the neighborhood scaling factor, SVI represents the scientific value index, and ESI represents the engineering safety index.

[0027] Furthermore, the objective function of the genetic intelligent algorithm is:

[0028]

[0029] In the formula, ObejFunc(w1,…,w n+m ,thre all ,thre1,…,thre n+m C) represents the objective function; P ci This indicates whether the modeling sample region i is a candidate landing area; 1 indicates yes, 0 indicates no. aj Indicates whether the modeling sample region i is a historical lunar exploration area or a publicly disclosed future target area; 1 indicates yes, 0 indicates no. Sum represents the number of modeling samples. w k Indicates the importance of any location selection metric parameter; Lowew k and Upw k These represent the lower and upper bounds of any location selection parameter, respectively; all This represents the threshold for determining whether a target area is a landing zone. j represents the optimal threshold for the location index factor of the j-th lunar month; C represents the neighborhood scaling factor.

[0030] Furthermore, the steps for obtaining the optimal addressing parameters specifically include:

[0031] Parameter encoding: Addressing parameters are encoded using real numbers;

[0032] Function definition: Define the objective function to be optimized, with the optimization direction being to minimize RMSE;

[0033] Control parameters: population size, maximum number of generations, crossover probability, mutation probability, and stopping conditions. The stopping conditions are set based on the tolerance for change and the maximum number of generations.

[0034] Initialize the population: Randomly generate the first generation population, which is the set of initial location parameters;

[0035] Calculate function value: Calculate the objective function value corresponding to each group of chromosomes in the population, and determine whether the algorithm has reached the iteration stopping condition. If yes, the algorithm ends; otherwise, proceed to the next step.

[0036] Operator rules: Obtain the combination of location parameters through population selection, population crossover, and population mutation;

[0037] Return to the step of calculating the function value, iteratively update the combination of addressing parameters until the algorithm ends, and return the optimal addressing parameters.

[0038] Furthermore, the genetic intelligent method uses the reliability of site selection as the evaluation criterion and the minimization of the root mean square error (RMSE) of modeling as the evaluation index to obtain the optimal site selection parameters.

[0039] Furthermore, it also includes:

[0040] The accuracy of the optimal addressing parameters is verified by metrics including: accuracy, precision, recall, and false alarm rate.

[0041] The present invention also provides an electronic device comprising: one or more processors; a memory; and one or more programs stored in the memory, said one or more programs including instructions for executing the genetically intelligent lunar exploration site selection method considering the exploration value index as described above.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] (1) This invention comprehensively constructs a lunar exploration value index model by considering the scientific value index and the engineering safety index. Compared with the sliding window method, which only considers single indicators such as slope and illumination, this invention achieves a comprehensive evaluation and precise quantification of the engineering and scientific value of candidate areas. Based on the genetic intelligent algorithm, it extracts and accurately measures the expert site selection parameters, thereby obtaining a highly reliable exploration area.

[0044] (2) This invention uses objective functions and constraints to construct a lunar exploration value model, which is a combination of various complex equations and inequalities. It considers spatial neighborhood constraints and the influence of random decision-making, reflecting the complexity of multi-objective site selection such as lunar landing, base construction, and scientific research station construction. The objective function cannot be solved by statistics, but heuristic algorithms can achieve its optimized solution, reflecting the core value of the GA algorithm.

[0045] (3) Based on the genetic intelligent algorithm, this invention uses the root mean square error of the objective function as the criterion to realize the extraction and accurate quantification of expert site selection rules. It is suitable for conducting experiments on the Moon and Mars where reliable data quality is poor and sources are scarce. It can extract rules in local areas of high-quality data and apply them to the entire Moon, especially to areas with poor quality data. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0047] Figure 2 This is a calibration diagram of learning samples and test samples within the lunar south pole research area in an embodiment of the present invention;

[0048] Figure 3 This is a map showing the detection value index within the study area in this embodiment of the invention.

[0049] Figure 4 This is a high-detection-value pixel map of the study area in this embodiment of the invention. Detailed Implementation

[0050] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0051] Example 1

[0052] This embodiment takes into account the genetically intelligent lunar exploration site selection method based on the exploration value index, such as... Figure 1 As shown, the method includes the following steps:

[0053] S1. Acquire various types of lunar data and construct a multi-objective indicator system for lunar landing site selection.

[0054] To date, humanity has accumulated a wealth of remote sensing data related to the Moon, providing crucial information on lunar surface topography, geological features, shallow subsurface structure, and material composition. Addressing the engineering safety and scientific objectives of landing site selection, this method integrates various types of lunar data, including lunar raster and vector data, and high-resolution topographic data, to spatially express constraint indicators, forming a multi-level indicator system for site selection, as shown in Table 1.

[0055] Table 1 Multi-level Indicator System for Lunar Site Selection

[0056]

[0057] S2. Based on the multi-objective index system, calculate the lunar site selection index factors and perform preprocessing.

[0058] S21. Collect 20-meter topographic data of the lunar south pole and calculate the topographic slope and roughness based on the topographic data; calculate the surface distance from all pixels in the study area to the nearest water ice exposure point based on the water ice exposure location and the lunar surface slope; collect vector surface data of the permanently shadowed area of ​​the lunar south pole, convert it into raster data, and calculate the surface distance from all pixels in the study area to the nearest permanently shadowed area based on the lunar surface slope.

[0059] S22. Collect distribution maps of lunar south pole geological units, extract vector geological unit boundaries, and calculate the kernel density of geological unit boundaries; collect average illumination maps and average Earth communication maps of the lunar south pole.

[0060] S23. Extract the maximum and minimum values ​​of each indicator's attributes, normalize all indicators to the 0-1 range, and transform the indicators from physical attribute dimensions to a unified dimensionless dimension; use the highest resolution among all factors as the benchmark, perform bilinear sampling on the low-resolution data to unify the spatial resolution among indicators; perform pixel spatial matching on all factors to eliminate errors between pixel positions.

[0061] S3. Based on the preprocessed lunar site selection index factors, calculate the scientific value index and engineering safety index to comprehensively construct a lunar exploration value index model.

[0062] The specific steps are as follows:

[0063] S31. Based on the site selection requirements, select representative scientific value index factors to form the scientific value index:

[0064]

[0065] In the formula, x and y represent the geographical coordinates of the candidate region; f i (1…n,norm)(x,y) represents n scientific site selection indicators for this region; SVI(x,y) represents the scientific exploration value index; w i This represents the importance of indicator i.

[0066] S32. Based on the site selection requirements, select representative engineering safety index factors to form the engineering safety index:

[0067]

[0068] In the formula, ESI(x,y) represents the engineering safety index; f j (1…m,norm)(x,y) represents the m engineering safety indicators for this region; w j This represents the importance of indicator j;

[0069] S33. Based on the scientific value index and the engineering safety index, the lunar exploration value index is constructed as follows:

[0070]

[0071] The formula specifically considers the engineering safety of pixels. Utilizing the relationship between the current pixel and its neighboring pixels, if the engineering safety index of the current pixel is less than the average of its neighboring pixels, the pixel's overall detection value index is reduced through adaptive shrinkage control; conversely, if the engineering safety index of the current pixel is greater than the average of its neighboring pixels, the pixel's overall detection value index is increased through adaptive expansion control. The adaptive shrinkage and expansion coefficients are adaptively calculated using a heuristic algorithm.

[0072] S4. Use a genetic intelligent algorithm to obtain the optimal site parameters of the lunar exploration value index model.

[0073] The area north of the Shackleton crater at the lunar south pole is a crucial target region for future lunar south pole exploration. This region is close to the crater, which may contain large amounts of water ice, necessitating in-situ exploration and verification. Furthermore, the crater's high elevation provides continuous sunlight, offering long-term solar energy support for lunar rovers and making it a vital strategic area for establishing a future lunar south pole station.

[0074] S41. Based on the engineering safety constraints of the station construction area, and using the constraints of a slope of less than 7° and average illumination and average communication of more than 40%, select areas in the area that meet the landing exploration safety requirements.

[0075] S42. Within areas that meet engineering safety requirements, scientific value is used as the evaluation criterion. The distance to the water ice hiding point and the distance to the permanent shadow zone are used to measure whether the candidate area is suitable as a landing area. Since the accuracy of the labeled samples is directly related to the accuracy of the decision-making site selection rules, the preferred samples used for learning must meet all engineering safety indicators and have high scientific safety value; the avoidance samples are areas that do not meet any engineering indicators or do not have scientific exploration value. Figure 2 The selection criteria for the samples include preferred and evasive regions for learning, and preferred and evasive regions for testing.

[0076] S43. In the sample, 80% of the preferred region and avoidance region are selected as training samples, and 20% are used as test samples to test the accuracy of the decision rule. The test indicators include accuracy, precision, recall, and false positive rate.

[0077] S44. The GA intelligent method is used to learn samples, and the site selection credibility is used as the evaluation criterion and the modeling error is used as the evaluation index to extract the comprehensive site selection decision model.

[0078] To maximize the probability of scientific exploration value while considering complex practical constraints in site selection rules, this project proposes to employ a Genetic Algorithm (GA) intelligent method to obtain site selection rules. The GA method will be used to obtain these rules, with site selection reliability as the evaluation criterion and minimizing the root mean squared error (RMSE) as the evaluation metric, thus mapping the problem from site selection to algorithmic problem. The objective function of this mapping is expressed as:

[0079]

[0080] In the formula, ObejFunc(w1,…,w n+m ,thre all ,thre1,…,thre n+m C) represents the objective function to be solved (i.e., the root mean square error of the location rule); P ci The calculation result indicating whether the modeling sample region i is a candidate landing region (1 if yes, 0 otherwise); P aj Indicates whether the modeling sample region i is a historical lunar exploration area or a publicly disclosed future target area (1 for yes, 0 for no); Sum represents the number of modeling samples; w k The parameter representing the importance of any location selection metric; Lowew k and Upw k These represent the lower and upper bounds of any location selection parameter, respectively; all This represents the threshold for determining whether a target area is a landing zone. j represents the preferred threshold for the j-th location factor; C represents the neighborhood scaling factor.

[0081] The lunar south pole has an extremely complex topography. Permanently shadowed areas, steep slopes, and large lunar volcanoes are unsuitable for landing, station construction, and base building. Therefore, a site selection factor with an optimal threshold of thre is introduced. j These constraints can serve as limitations to prevent site selection from entering dangerous areas. Furthermore, neighborhood influences and changes in decision-making can also lead to site changes; this model utilizes a stochastic perturbation method to simulate these uncertainties. The aforementioned constraints can be expressed as a combination of complex equations and inequalities, reflecting the complexity of multi-objective site selection for lunar landing, base construction, and research station construction. Since this objective function cannot be solved statistically, heuristic algorithms can achieve its optimized solution, demonstrating the core value of the GA algorithm.

[0082] S45 and GA are typical biological evolution heuristic algorithms that search for optimal solutions by simulating the natural selection and genetic mechanisms of biological evolution. They are widely used in remote sensing and geographic information systems. This method aims to utilize modeling samples within the target area to mine optimal site selection parameters through GA, avoiding the drawbacks of manually setting weights. The main steps of GA in mining site selection parameters are as follows:

[0083] Step 1: Parameter Encoding: Encode the addressing parameters using real numbers;

[0084] Step 2: Function definition: Define the objective function to be optimized, with the optimization direction being to minimize RMSE;

[0085] Step 3: Control parameters: population size (20 times the number of parameters to be solved), maximum number of generations (5000 generations), crossover probability (0.4~0.99), mutation probability (0.001~0.1) and stopping conditions. Set the stopping conditions based on the tolerance for change and the maximum number of generations.

[0086] Step 4: Initialize the population: Randomly generate the first generation population, which is the set of initial location parameters.

[0087] Step 5: Calculate the function value: Calculate the objective function value corresponding to each group of chromosomes in the population, and determine whether the algorithm has reached the iteration stopping condition. If yes, proceed to step 8; if no, proceed to step 6.

[0088] Step 6: Operator Rules: Population selection: Based on the roulette wheel method, individuals with low objective function values ​​(objective function represents error) are selected as parents for inheritance to retain high-quality location parameter combinations; Population crossover: Under the condition that the generated random number is greater than the crossover probability, single-point crossover is performed between parents to update the location parameters based on the parents; Population mutation: Under the condition that the mutation probability is greater than the mutation probability, local segments in the location parameters are changed to update the location parameter combination.

[0089] Step 7: Return to Step 5, calculate the objective function of the new generation population, and determine whether the algorithm has ended;

[0090] Step 8: The algorithm ends and returns the optimized addressing parameters.

[0091] Table 2 shows the results of the location decision rules learned by the GA algorithm.

[0092] Table 2 Results of Site Selection Decision Rule Parameters

[0093]

[0094] S46. Verify the accuracy of the site selection decision-making integrated model in the test sample.

[0095] Step 1: Apply the extracted site selection decision rule parameters to the lunar exploration value index model to obtain an updated lunar exploration value index model.

[0096] Step 2: Evaluate the location decision error of the updated model: This step mainly uses the extracted location decision rule parameters to calculate the location results for each training sample and test sample, compares them with the true values, and infers the accuracy of the location model parameters. Table 3 shows the model validation results.

[0097] Table 3 Model Validation Results

[0098]

[0099] The results from the training and testing samples shown in Table 3 reveal that the site selection decision model achieves an accuracy of 99.87% and a recall of 99.32% in the training sample, while all three metrics (accuracy, precision, and recall) are 100% in the testing sample. This indicates that the extracted site selection decision model rules can accurately learn the expert site selection decision-making process and can be used for calculating exploration value indices on a larger scale to extract suitable landing areas for lunar exploration.

[0100] S5. Based on the lunar exploration value index model and optimal site parameters, calculate the exploration value index and adaptively select high-value exploration areas using threshold screening.

[0101] The specific steps are as follows:

[0102] S51. Based on the extracted site selection decision model rules, apply them to all pixels in the study area to obtain the lunar exploration value index for each pixel.

[0103] S52. Using the lunar exploration value index and adaptive threshold, calculate whether each pixel is suitable as a candidate landing area for lunar exploration.

[0104] This concludes the entire process of this embodiment. Figure 3 It can display the detection value index of each pixel in the study area north of the Shackleton crater at the lunar south pole. Figure 4 The optimal landing areas extracted after area and shape constraints are shown. It can be seen that the optimal landing areas are flat and suitable for landing and lunar exploration activities.

[0105] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] Example 2

[0107] This embodiment provides an electronic device, including: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs including instructions for executing the genetically intelligent lunar exploration site selection method considering the exploration value index as described in Embodiment 1.

[0108] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0109] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0110] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0111] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0112] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

Claims

1. A genetically-based intelligent lunar exploration site selection method that takes into account the exploration value index, characterized in that, Includes the following steps: Acquire various types of lunar data to construct a multi-objective indicator system for lunar landing site selection; Based on the aforementioned multi-objective index system, lunar site selection index factors are calculated and preprocessed. Based on the preprocessed lunar site selection index factors, the scientific value index and engineering safety index are calculated to comprehensively construct a lunar exploration value index model. The specific steps for comprehensively constructing the lunar exploration value index model include: Based on the requirements of the site selection mission, scientific value index factors are selected from the lunar site selection index factors to form a scientific value index. Based on the requirements of the site selection mission, engineering safety index factors are selected from the lunar site selection index factors to form an engineering safety index. Based on the aforementioned scientific value index and engineering safety index, a lunar exploration value index model is constructed. The expressions for the scientific value index and the engineering safety index are as follows: In the formula, x and y Geographic coordinates representing the candidate region SVI ( x , y () represents the scientific value index. w i Representing scientific value index factors i The importance of; ESI ( x , y ) represents the engineering safety index. w j Representative engineering safety index factors j The importance of; The detection value index model is as follows: In the formula, As a value index for lunar exploration. C Represents the neighborhood scaling factor. SVI Represents the scientific value index. ESI The representative engineering safety index; the optimal site selection parameters of the lunar exploration value index model are obtained using a genetic intelligent algorithm, the objective function of which is: In the formula, Represent the objective function; P ci Represents the modeling sample area i The result indicates whether it is a candidate landing area; 1 indicates yes, 0 indicates no. P aj Represents the modeling sample area i Whether it is a historical area of ​​lunar exploration or a publicly announced future target area, 1 if yes, 0 otherwise; Sum Indicates the number of samples in the modeling; w k Indicate the importance of any location selection parameter; Lowew k and Upw k These represent the lower and upper bounds of any location selection index parameter, respectively. thre all This represents the threshold for determining the exploration value index of a potential landing area. thre j Representing the j The optimal threshold for lunar site selection index factors; C Represents the neighborhood scaling factor; Based on the lunar exploration value index model and optimal site selection parameters, the exploration value index is calculated, and high-value exploration areas are selected through adaptive threshold screening.

2. The genetically-based intelligent lunar exploration site selection method considering the exploration value index according to claim 1, characterized in that, The specific steps for calculating and preprocessing the lunar site selection index factors include: Calculate the corresponding lunar site selection index factors based on the indicators in the multi-objective index system. The spatial reference of the lunar site selection index factors is unified, and coordinate matching is performed among the lunar site selection index factors to unify the data resolution.

3. The genetically-based intelligent lunar exploration site selection method considering the exploration value index according to claim 1, characterized in that, The steps for obtaining the optimal addressing parameters specifically include: Parameter encoding: Addressing parameters are encoded using real numbers; Function definition: Define the objective function to be optimized, with the optimization direction being to minimize RMSE; Control parameters: population size, maximum number of generations, crossover probability, mutation probability, and stopping conditions. The stopping conditions are set based on the tolerance for change and the maximum number of generations. Initialize the population: Randomly generate the first generation population, which is the set of initial location parameters; Calculate function value: Calculate the objective function value corresponding to each group of chromosomes in the population, and determine whether the algorithm has reached the iteration stopping condition. If yes, the algorithm ends; otherwise, proceed to the next step. Operator rules: Obtain the combination of location parameters through population selection, population crossover, and population mutation; Return to the step of calculating the function value, iteratively update the combination of addressing parameters until the algorithm ends, and return the optimal addressing parameters.

4. The genetically intelligent lunar exploration site selection method considering the exploration value index according to claim 1, characterized in that, The genetic intelligent algorithm uses the reliability of site selection as the evaluation criterion and the minimization of the root mean square error (RMSE) of modeling as the evaluation index to obtain the optimal site selection parameters.

5. The genetically-based intelligent lunar exploration site selection method considering the exploration value index according to claim 1, characterized in that, Also includes: The accuracy of the optimal addressing parameters is verified by metrics including: accuracy, precision, recall, and false alarm rate.

6. An electronic device, characterized in that, include: One or more processors; Memory; and One or more programs stored in a memory, the one or more programs including instructions for executing the genetically intelligent lunar exploration site selection method taking into account the exploration value index as described in any one of claims 1-5.

Images