The safety of lunar landing sites directly impacts the success of lunar exploration missions. This study develops a data-driven predictive model based on machine learning, focusing on engineering safety to assess the suitability of lunar landing sites and provide insights into key factors and feature representations. Six critical engineering factors were selected as constraints for evaluation: slope, elevation, roughness, hillshade, optical maturity, and rock abundance. The XGBoost model was employed to simulate and predict the characteristics of landing areas and Bayesian optimization was used to fine-tune the model’s key hyperparameters, enhancing its predictive performance. The results demonstrate that this method effectively extracts relevant features from multi-source remote sensing data and quantifies the suitability of landing zones, achieving an accuracy of 96% in identifying landing sites (at a resolution of 0.1° × 0.1°), with AUC values exceeding 95%. Notably, slope was recognized as the most critical factor affecting safety. Compared to assessment processes based on Convolutional Neural Networks (CNNs) and Random Forest (RF) models, XGBoost showed superior performance in handling missing values and evaluating feature importance accuracy. The findings suggest that the BO-XGBoost model shows notable classification performance in evaluating the suitability of lunar landing sites, which may provide valuable support for future landing missions and contribute to optimizing lunar exploration efforts.

The samples from lunar farside have great significance for the study of the Moon, and even the solar system. Chang’e-6 landed successfully on the southern mare of the Apollo basin and returned ~2 kg of samples from lunar farside. To provide a better understanding for the background of the returned samples, we conducted detailed crater size-frequency distribution (CSFD) measurements in the Chang’e-6 landing region, the southern mare of the Apollo basin. The southern mare is divided into the western mare (W region) and the eastern mare (E region), and then subdivided into five subunits (W1, W2, W3, W4, W5) and three units (E1, E2, E3), respectively, according to the elevation, TiO₂, and FeO abundances. Within the W2 and W5 region, more detailed subunits were separated out. The results show that the southern mare surface was active during two epochs, the Imbrian period and the Eratosthenian period. The basalt eruption lasted for ~1.7 Ga, from 3.28 Ga of the eastern mare to 1.54 Ga of the western mare. The W region is younger than the E region, while the three units of the E region have an age of ~3.2 Ga. The ages of the western mare basalts range from 2.98 Ga to 1.54 Ga, lasting for 1.4 Ga. It is worth noting that the age of the basalt at the Chang’e-6 sampling site is ~1.68 Ga, indicating the samples returned may include components with this very young age.

The specific duration between the impact event and subsequent volcanic flows is highly variable based on previous works. The method of crater size-frequency distribution (CSFD) has been previously used to date the basalt in Orientale Basin, which yielded inconsistent resultant Absolute Model Age (AMA) ranges. The inconsistency may be attributed to the choice of counting area and identified superposed craters. In this study, we integrated the Chang’E-2 (CE-2) imaging data (7 m/pix) and the IIM and 20 m CE-2 DTMS data, re-divided Mare Orientale, and re-estimated the age of the basalts there. The ages revealed that (1) the central basalts had multiphase eruptions, beginning at 3.77 Ga (30 My after the impact event) with the longest duration of 1.51 Gy; (2) the edge basalts have a similar features as the central basalts, beginning at 3.75–3.50 Ga (50–300 My after the impact) with the longest duration of 0.67 Gy. Compared with the basalts along the basinal margin, the central basalts have higher Ti but lower Mg^# contents, consistent with the basaltic magma fractionation trend. Spatial distribution characteristics indicate that the basalt eruption occurred in the impact direction upstream and in the center, but almost absent in the impact direction downstream. Accordingly, we speculate that the longevity of the lunar mare basaltic volcanism was affected by gravity changes, material balance, and other post-impact processes.

The permanently shadowed regions of the lunar South Pole have become a key target for international lunar exploration due to their unique scientific value and engineering challenges. In order to effectively screen suitable landing zones near the lunar South Pole, this research proposes a comprehensive evaluation method based on a self-organizing map (SOM). Using multi-source remote sensing data, the method classifies and analyzes candidate landing zones by combining scientific purposes (such as hydrogen abundance, iron oxide abundance, gravity anomalies, water ice distance analysis, and geological features) and engineering constraints (such as Sun visibility, Earth visibility, slope, and roughness). Through automatic clustering, the SOM model finds the important regions. Subsequently, it integrates with a supervised learning model, a random forest, to determine the feature importance weights in more detail. The results from the research indicate the following: the areas suitable for landing account for 9.05%, 5.95%, and 5.08% in the engineering, scientific, and synthesized perspectives, respectively. In the weighting analysis of the comprehensive data, the weights of Earth visibility, hydrogen abundance, kilometer-scale roughness, and slope data all account for more than 10%, and these are thought to be the four most important factors in the automated site selection process. Furthermore, the kilometer-scale roughness data are more important in the comprehensive weighting, which is in line with the finding that the kilometer-scale roughness data represent both surface roughness from an engineering perspective and bedrock geology from a scientific one. In this study, a local examination of typical impact craters is performed, and it is confirmed that all 10 possible landing sites suggested by earlier authors are within the appropriate landing range. The findings demonstrate that the SOM-model-based analysis approach can successfully assess lunar South Pole landing areas while taking multiple constraints into account, uncovering spatial distribution features of the region, and offering a rationale for choosing desired landing locations.

Tectonic features on the Moon can reflect the state of stress during the formation of the structure, and sinuous rilles can provide further insight into the tectonic-thermal evolution of the Moon. Manual visual interpretation is the primary method for extracting these linear structures due to their complex morphology. However, extracting these features from the vast amount of lunar remote sensing data requires significant time and effort from researchers, especially for small-scale tectonic features, such as wrinkle ridges, lobate scarps, and high-relief ridges. In order to enhance the efficiency of linear structure detection, this paper conducts research on the automatic detection method of linear structures using sinuous rilles as an example case. In this paper, a multimodal semantic segmentation method, “Sinuous Rille Network (SR-Net)”, for detecting sinuous rilles is proposed based on DeepLabv3+. This method combines advanced techniques such as ECA-ResNet and dynamic feature fusion. Compared to other networks, such as PSPNet, ResUNet, and DeepLabv3+, SR-Net demonstrates superior precision (95.20%) and recall (92.18%) on the multimodal sinuous rille test set. The trained SR-Net was applied in detecting lunar sinuous rilles within the range of 60°S to 60°N latitude. A new catalogue of sinuous rilles was generated based on the results of the detection process. The methodology proposed in this paper is not confined to the detection of sinuous rilles; with further improvements, it can be extended to the detection of other linear structures.

The evolution of the Moon is driven by both endogenic (e.g., magmatism) and exogenic processes (e.g., impact). The lunar surface can be divided into 3 first-order tectonic units based on differences in geochemistry, crustal thickness, topography, and distribution of structures. However, the interpreted boundaries demarcated by different features varied widely. As research progresses, the understanding of the lunar structure is continuously improving, and new types of structures are constantly being discovered. The previous structural classification system needs to be updated. According to the major geological events and dynamic evolution, the evolutionary history of the Moon can be divided into 3 stages and 1 pivotal event. The first stage (4.52 to 4.3 Ga) is the evolution of the magmatic ocean, and it was dominated by endogenic processes. The formation of South Pole-Aitken (SPA) basin (~4.3 Ga) is the pivotal event of crustal evolution and indicates that the lunar crust had cooled and consolidated to sufficient rigidity to preserve structures. Both endogenic and exogenic processes were active in the second stage (4.3 to 3.0 Ga), which results in numerous impact basins, mare basalt flooding, and different types of associated structures. The last stage (3.0 Ga to the present) is late neotectonic activity, which has weak modification of the tectonic framework. Response of tectonic framework and structure to lunar major geological events had been organized and discussed in this paper, and key scientific issues are summarized. This study can provide reference and support for implementation of subsequent lunar exploration projects.