Lunar volcanic domes are essential windows into the local magmatic activities on the Moon. Classification of domes is a useful way to figure out the relationship between dome appearances and formation processes. Previous studies of dome classification were manually or semi-automatically carried out either qualitatively or quantitively. We applied an unsupervised machine-learning method to domes that are annularly or radially distributed around Gardner, a unique central-vent volcano located in the northern part of the Mare Tranquillitatis. High-resolution lunar imaging and spectral data were used to extract morphometric and spectral properties of domes in both the Gardner volcano and its surrounding region in the Mare Tranquillitatis. An integrated robust Fuzzy C-Means clustering algorithm was performed on 120 combinations of five morphometric (diameter, area, height, surface volume, and slope) and two elemental features (FeO and TiO₂ contents) to find the optimum combination. Rheological features of domes and their dike formation parameters were calculated for dome-forming lava explanations. Results show that diameter, area, surface volume, and slope are the selected optimum features for dome clustering. 54 studied domes can be grouped into four dome clusters (DC1 to DC4). DC1 domes are relatively small, steep, and close to the Gardner volcano, with forming lavas of high viscosities and low effusion rates, representing the latest Eratosthenian dome formation stage of the Gardner volcano. Domes of DC2 to DC4 are relatively large, smooth, and widely distributed, with forming lavas of low viscosities and high effusion rates, representing magmatic activities varying from Imbrian to Eratosthenian in the northern Mare Tranquillitatis. The integrated algorithm provides a new and independent way to figure out the representative properties of lunar domes and helps us further clarify the relationship between dome clusters and local magma activities of the Moon.

Viscosity is a fundamental physical parameter governing the generation, transport, and eruption of geological melts, dictating magma ascent rates, eruption styles, and the kinetics of physicochemical processes. On Earth, melts viscosities have been widely measured from various rock samples through high T-P (temperature & pressure) experiments, and a continuous viscosity-temperature-pressure (V-T-P) dependence can be obtained by different melt viscosity models. However, due to significant compositional differences, particularly in iron and titanium oxides between lunar and terrestrial basalts, no existing model can be simply used to predict magma viscosity on the Moon.In this study, we have collected and trained on a comprehensive dataset of 28898 hand-curated melt measurements (compositions, pressure, temperatures and viscosity), including typical lunar melt types of ferrobasaltic melts, Apollo 15C green glass, Apollo 17 orange glass, Apollo 14 black glass, as well as synthetic high-titanium mare basalts and KREEP basalts. We have employed Kolmogorov-Arnold Networks (KANs) to construct a deep learning model and established a relationship between lunar melt viscosity and its temperature, pressure, and composition (V-T-P-C). Unlike traditional Multi-Layer Perceptrons (MLPs), KANs utilize learnable spline functions rather than fixed activation functions. This architecture offers superior interpretability and generalization capabilities, making it particularly suitable for predicting viscosity under complex thermodynamic conditions.The predicted rheological behavior of KREEP lunar silicate melts (Apollo samples) from KANs are well consistent with experimental measurements. Taking into account the compositions of basalts obtained from Chang’e 5 and 6 sampling, model suggests that the viscosity values ( Pa·s ) of young basalts (~2.0 Ga for Chang’e 5 and ~2.8 Ga for Chang’e 6) are ~2.5 orders of magnitude lower than that of relatively older Apollo-type basalts (>3.0 Ga) under the same T-P conditions.

The chronology function and production function have been widely used to derive the model ages of lunar mare regions from crater size-frequency distributions (CSFDs). Challenges remain in homogenous counting area selection, crater saturation and crater rim identification. Geological unit-based ages are also difficult to study the continuous surface evolution among adjacent areas. Using regression-learning models, we have tried a new method on the Em4 unit of the Chang’e 5 landing area to explore a quantitative relationship between ages and surface morphometric expressions by using texture features. Four features (Contrast, Energy, Entropy and Homogeneity), together with a stepwise linear model (SL) and a linear support-vector-machine model (LS) are well selected to produce a pixel-level continuous age map of the Em4 unit. Mean age values of 1.75 ±0.26 Ga and 1.69 ±0.22 Ga obtained respectively from the two models are consistent with the ages of Chang’e 5 samples returned from this area. Both texture features and age maps are separated along the NW-SE sinuous rilles (Rima Sharp and Rima Mairan). Comprehensively considering geology, geomorphology, and newly retrieved ages of the study region, we have proposed a three-stage evolution process for the Em4 unit. Our new age-retrieving method is useful to obtain a pixel-level high-resolution age map in the study region and has the potential to be widely used in other lunar mare areas.