This paper explores and discusses the revolutionary applications of digital twin technology in space environments and its profound impact on future space exploration activities. Originating from a proposal by the National Aeronautics and Space Administration (NASA) in 2002, digital twin technology aims to enhance the safety and reliability of space missions by creating precise virtual models. As the technology has evolved, its applications have successfully expanded beyond aerospace to include Industry 4.0, healthcare, and urban management, demonstrating remarkable cross-industry adaptability and broad impact. In space applications, digital twin technology can not only improve spacecraft design and maintenance processes but also enhance the efficiency of mission planning and execution. It plays a crucial role in astronaut training and emergency response as well. Particularly in extreme space conditions, this technology provides real-time monitoring and fault prediction, significantly enhancing mission safety and success rates. However, despite its recognized potential, the implementation of digital twins in space environments faces numerous challenges, including data transmission delays, model accuracy, and the design of user–system interactions. In the future, as artificial intelligence (AI) and machine learning (ML) technologies become mature and integrated, the digital twin will play a more central role in space missions, especially in remote operations, complex system management, and deep space exploration. This article is to overview key technical features, application examples, and challenges of digital twin technology, aiming to provide a comprehensive reference framework for researchers and developers while inspiring further in-depth studies and innovative applications.

Impact craters are the most prominent features on the surface of the Moon, Mars, and Mercury. They play an essential role in constructing lunar bases, the dating of Mars and Mercury, and the surface exploration of other celestial bodies. The traditional crater detection algorithms (CDA) are mainly based on manual interpretation which is combined with classical image processing techniques. The traditional CDAs are, however, inefficient for detecting smaller or overlapped impact craters. In this paper, we propose a Split-Attention Networks with Self-Calibrated Convolution (SCNeSt) architecture, in which the channel-wise attention with multi-path representation and self-calibrated convolutions can generate more prosperous and more discriminative feature representations. The algorithm first extracts the crater feature model under the well-known target detection R-FCN network framework. The trained models are then applied to detecting the impact craters on Mercury and Mars using the transfer learning method. In the lunar impact crater detection experiment, we managed to extract a total of 157,389 impact craters with diameters between 0.6 and 860 km. Our proposed model outperforms the ResNet, ResNeXt, ScNet, and ResNeSt models in terms of recall rate and accuracy is more efficient than that other residual network models. Without training for Mars and Mercury remote sensing data, our model can also identify craters of different scales and demonstrates outstanding robustness and transferability.

The Permanently Shadowed Regions (PSRs) of the lunar south pole have never been directly sampled. To explore and discover lunar resources, the Chinese lunar south pole exploration mission is scheduled to land in direct sunlight near the PSR, where sampling and analysis will be carried out. The selection of sites for lunar landing sampling sites is one of the key steps of the mission. The main factors affecting the site selection are the distribution of PSRs, lunar surface slopes, rock distribution, light intensity, and maximum temperature. In this paper, the main factors affecting site selection are analyzed based on lunar multi-source remote sensing data. Combined with previous engineering constraints, we then propose a comprehensive multi-factor fuzzy cognition and selection model for the lunar south site selection. An analytical model based on a fuzzy cognitive map algorithm is also established. Furthermore, to make a preliminary landing area selection, we determine the evaluation index for the candidate landing areas using fuzzy reasoning. Using the proposed model and combined scoring index, we also verify and analyze the prominent impact craters at the lunar south pole. The scores of de Gerlache (88.48°S 88.34°W), Shackleton (89.67°S 129.78°E), and Amundsen (84.5°S, 82.8°E) craters are determined using fuzzy interference as 0.816, 0.814, and 0.784, respectively. Moreover, using our proposed approach, we identify feasible landing sites around the de Gerlache crater close to the PSR to facilitate discovery of water ice exposures in future missions. The proposed method is capable of evaluating alternative landing zones subject to multiple engineering constraints on the Moon or Mars based on the existing data.

Air quality is a significant environmental issue among the Chinese people and even the global population, and it affects both human health and the Earth’s long-term sustainability. In this study, we proposed a multiperspective, high-dimensional spatiotemporal data visualization and interactive analysis method, and we studied and analyzed the relationship between the air quality and several influencing factors, including meteorology, population, and economics. Six visualization methods were integrated in this study, each specifically designed and improved for visualization analysis purposes. To reveal the spatiotemporal distribution and potential impact of the air quality, we designed a comprehensive coupled visual interactive analysis approach visually express both high-dimensional and spatiotemporal attributes, reveal the overall situation and explain the relationship between attributes. We clarified the current spatiotemporal distribution, development trends, and influencing factors of the air quality in China through interactive visual analysis of a 25-dimensional dataset involving 31 Chinese provinces. We also verified the correctness and effectiveness of relevant policies and demonstrated the advantages of our method.

Synthetic Aperture Radar (SAR) is highly valuable for target detection due to its all-weather, day-night operational capability and certain ground penetration potential. However, traditional SAR target detection methods often directly adapt algorithms designed for optical imagery, simplistically treating SAR data as grayscale images. This approach overlooks SAR’s unique physical nature, failing to account for key factors such as backscatter variations from different polarizations, target representation changes across resolutions, and detection threshold shifts due to clutter background heterogeneity. Consequently, these limitations lead to insufficient cross-polarization adaptability, feature masking, and degraded recognition accuracy due to clutter interference. To address these challenges, this paper systematically reviews recent research advances in SAR target detection, focusing on physical constraints including polarization characteristics, scattering mechanisms, signal-domain properties, and resolution effects. Finally, it outlines promising research directions to guide future developments in physics-aware SAR target detection.

Orthophoto generation is a popular topic in aerial photogrammetry and 3D reconstruction. It is generally computationally expensive with large memory consumption. Inspired by the simultaneous localization and mapping (SLAM) workflow, this paper presents an online sequential orthophoto mosaicing solution for large baseline high-resolution aerial images with high efficiency and novel precision. An appearance and spatial correlation-constrained fast low-overlap neighbor candidate query and matching strategy is used for efficient and robust global matching. Instead of estimating 3D positions of sparse mappoints, which is outlier sensitive, we propose to describe the ground reconstruction with multiple stitching planes, where parameters are reduced for fast nonconvex graph optimization. GPS information is also fused along with six degrees of freedom (6-DOF) pose estimation, which not only provides georeferenced coordinates, but also converges property and robustness. An incremental orthophoto is generated by fusing the latest images with adaptive weighted multiband algorithm, and all results are tiled with level of detail (LoD) support for efficient rendering and further disk cache for reducing memory usages. Public datasets are evaluated by comparing state-of-the-art software. Results show that our system outputs orthophoto with novel efficiency, quality, and robustness in real-time. An android commercial application is developed for online stitching with DJIdrones, considering the excellent performance of our algorithm.