Research On The Optimization Method Of Lunar Landing Area Based On Machine Learning

At present,the selection of lunar landing areas is mostly determined by experts’ argumentation and experience.Generally,it is artificially limited to a small zone,and there are few effective quantitative models for landing areas.Under the premise that big data,artificial intelligence,and other technologies are becoming increasingly mature,with in-depth analysis and the mining of lunar-related digital data,it is possible to automatically optimize the landing zones in the whole moon.Considering the factors of engineering constraints,scientific objectives and resource requirements,this paper proposes a new method for blind selection of the appropriate landing area of the probe for the whole moon,which comprehensively applies the weights of evidence(Wo E),the fractals and machine learning.The results achieved are as follows:(1)A method based on weights of evidence and fractals to optimize the landing area for the whole moon is proposed.The method takes the thickness of the lunar crust,roughness,slope,digital elevation model,gravity gradient,iron oxide distribution,and lunar soil optical maturity as evidence layers,and known landing sites as the target layer.After all moon data are divided into grids,the prior probability of each evidence factor,the in-cell weight of each evidence factor,and the Bayesian posterior probability are calculated.According to the semi-parabolic distribution in the fuzzy distribution,the fuzzy membership degree of the impact crater radius is presented and the complexity of the number of impact craters in a cell is calculated.The distribution complexity of impact craters in each cell is calculated according to the fractal.The result of the weights of evidence is further constrained by the complexity of the number of cells and the complexity of the distribution,and the posterior probability map of suitable landings is finally obtained.(2)The full moon landing suitability model based on decision tree and random forest is designed and implemented.Using the posterior probability results of weights of evidence as a training set,decision tree and random forest models are used to predict the suitability of the full moon landing area at higher resolution.Ultimately,the goal of blind selection and optimization of the landing area can be achieved.The prediction accuracy is up to 99.85%.It takes less time,and the boundary of the full moon forecast results is smooth,and the local suitable landing area is smaller and more accurate,which shows the effectiveness of the decision tree model.In addition,the accuracy of training based on random forest model is also up to 99%.Similarly,better results were obtained.The known landing points and the artificially preferred landing zones roughly distributed in or around high probability areas.(3)The effectiveness of the optimization method designed in this paper is verified by real data.By comparing and analyzing the posterior probability map of the landing areas with the landing points and manual optimal landing areas,it is found that 84% and 82.6% fall within the suitable landing area,respectively.Among them,the first gradient is 58% and 58.7%,and the second gradient is 26% and 23.9%.The results at different resolutions are relatively stable and are consistent with the distribution of craters or basins in the lunar mantle and the spatial distribution of olivine,which proves the effectiveness and feasibility of this method.(4)The full moon landing area optimization subsystem has been launched for service.Relevant algorithms and modules have been integrated into the digital lunar platform to form an automatic location selection system.After testing,the majority of important areas such as Rima Bodde were located in high probability locations,which again verifies the correctness of the location method.