30 May 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
The identification of optimal landing sites is a critical first step for successful missions to the Moon and other extraterrestrial bodies, necessitating the integration of various environmental factors over large spatial scales. At the lunar south pole, site selection must balance engineering safety with areas of high scientific interest, requiring extensive analysis of potential locations. Although intelligent algorithms have been increasingly investigated for this purpose, the application of deep learning techniques in landing site selection remains unexplored. In this study, we employ one-dimensional convolutional neural networks (1D-CNN) to quantitatively assess potential landing sites for exploration and lunar base construction, considering both scientific and engineering criteria. We also evaluate the influence of various factors on site selection using Shapley Additive Explanations (SHAP) values. The 1D-CNN model demonstrates robust performance across training, validation and testing phases. Potential landing sites identified comprise less than 1% of the total study area, with factors such as visibility, volatile distribution, topography, and geological characteristics playing crucial roles. By applying operational constraints, we delineate sites suitable for direct landings and further refine this subset for base construction based on stringent requirements for resource utilization and energy sustainability. The combined use of CNN and SHAP enables more effective potential site screening and a deeper understanding of the factors influencing selection. Our findings offer a valuable framework for future lunar south pole expeditions, potentially minimizing manual survey efforts and enhancing the precision of landing site selection.
28 February 2023 in Journal of Geophysical Research: Planets
18 February 2025 in IEEE Transactions on Geoscience and Remote Sensing
The mineral composition of lunar regolith influences brightness temperature (TB) as observed by the microwave radiometer (MRM); however, the large-scale spatial relationship between TB and mineral abundance has yet to be sufficiently revealed. This study aims to quantify the impact of specific mineral abundances (plagioclase and ilmenite) on TB distribution, using MRM 37-GHz data from Chang’E-2 and mineral abundance products from Kaguya. We applied hour angle correction and latitude normalization to produce high-accuracy TB maps and developed a self-adaptive moving-window method to remove strip noise to produce higher precision mineral abundance maps. Using these two types of maps, we performed comprehensive large-scale spatial analysis of TB and mineral abundance using a bivariate spatial autocorrelation model and a geographically weighted regression (GWR) approach considering spatial similarity and heterogeneity, respectively. The bivariate analysis indicates a negative spatial correlation between TB and plagioclase abundance, while a positive spatial correlation between TB and ilmenite abundance. In addition, bivariate anomalies, including both hot and cold spots of diurnal TB amplitude (i.e., noon minus nighttime), were identified through the simultaneous consideration of TB and mineral abundance. The GWR analysis reveals regional variations in the impact of mineral abundances on diurnal TB amplitudes. These correlations can be attributed to the spatial distributions and variations in TB, which arise from the unique dielectric and thermal properties of minerals across distinct regions on the Moon. These findings contribute to a better understanding of subsurface thermal behavior and regimes, enhancing our comprehension of lunar evolution.
15 July 2024 in Earth and Space Science
Solar irradiance received at the lunar surface is crucial for interpreting brightness temperatures detected by orbiters and for understanding the thermal, physical, and dielectric properties of the lunar regolith. We developed a real‐time effect solar irradiance (ESI) model that accounts for the influence of surface relief and terrain shading. This model was integrated with a standard thermal model to examine ESI fluctuations and their impacts on the diurnal physical temperature variations. To assess the effects of spatial resolution, we selected four locations with significant ESI disparities for simulation, then compared lunar surface temperatures at various spatial scales, ranging from 20 m to 25 km. Utilizing brightness temperature data obtained from the Chang'E‐2 (CE‐2) microwave radiometer (MRM), we integrated the shallow physical temperature profiles with the radiative transfer equation to simulate brightness temperatures and determine dielectric loss at different frequencies. In the Von Kármán crater, the received ESI exhibits a cyclical pattern of approximately 18 years and areas with rugged topography may exhibit larger ESI variations (∼7%). We found that the spatial resolution of ESI has a minimal effect on the physical and brightness temperatures at resolutions of 10 km or coarser. At the shallow layer, the average dielectric loss values are 0.0128–0.0170, 0.0083–0.0110, 0.0055–0.0073, and 0.0061–0.0081 for the CE‐2 frequencies of 3, 7.8, 19.35, and 37 GHz, respectively. The integration of real‐time ESI modeling, thermal dynamics, radiative transfer equations, and observational data enhances our comprehension of the physical temperature profile and thermal characteristics of shallow regolith.
14 July 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In this study, we proposed a pixel-level projection method for fine particulate matter (PM 2.5 ) over a long term and across a large area using a combination of Landsat images, PM 2.5 data from monitoring stations, and historical gridded PM 2.5 data. We considered the spatial dependence effects of the particulate matter using a spatial lag model to quantify the relationship between PM 2.5 concentration and land coverage indices, where the latter were calculated by the built-up, vegetation, and water indices. The future land coverage indices for the pixel-level projection of PM 2.5 were derived from the future land-use scenario predicted by the Futureland model. We applied the method to analyze the spatial patterns of PM 2.5 in the Yangtze River Delta (YRD), China from 2000 to 2020, then projected its pixel-level scenario in 2030. The projected PM 2.5 shows high concentrations in the north and low in the south and temporally decreases compared to 2010. The projection of the fine-grained PM 2.5 scenario can help adjust YRD's environmental and industrial policies, as well as implement its management strategies for sustainable urban development. Our method can be used to predict future patterns not only for long-term and large-scale pixel-level PM 2.5 concentrations but also for other environmental parameters.