A novel satellite target recognition method based on radar data partition and deep learning techniques is proposed in this paper. For the radar satellite recognition task, orbital altitude is introduced as a distinct and accessible feature to divide radar data. On this basis, we design a new distance metric for HRRPs called normalized angular distance divided by correlation coefficient (NADDCC), and a hierarchical clustering method based on this distance metric is applied to segment the radar observation angular domain. Using the above technology, the radar data partition is completed and multiple HRRP data clusters are obtained. To further mine the essential features in HRRPs, a GRU-SVM model is designed and firstly applied for radar HRRP target recognition. It consists of a multi-layer GRU neural network as a deep feature extractor and linear SVM as a classifier. By training, GRU neural network successfully extracts effective and highly distinguishable features of HRRPs, and feature visualization technology shows its advantages. Furthermore, the performance testing and comparison experiments also demonstrate that GRU neural network possesses better comprehensive performance for HRRP target recognition than LSTM neural network and conventional RNN, and the recognition performance of our method is almost better than that of other several common feature extraction methods or no data partition.

The rapid proliferation of resident space objects has made space situational awareness critically dependent on accurate characterization of non-cooperative targets using photometric light curves. This review provides a comprehensive examination of data-driven approaches for space object photometric prediction, synthesizing research across optical scattering characterization, shape and attitude inversion methodologies, and intelligent analysis techniques based on machine learning and deep learning. The evolution from traditional physics-based models to contemporary data-driven paradigms is systematically analyzed, revealing fundamental trade-offs between physical interpretability, computational efficiency, and predictive accuracy. Key findings indicate that while physical bidirectional reflectance distribution function (BRDF) models provide rigorous foundations, their computational demands and prior knowledge requirements limit operational applicability; conversely, deep learning has demonstrated superior predictive accuracy in existing comparative studies, although this conclusion is qualified by the absence of standardized public benchmarks, and it also suffers from interpretability deficits and simulation-to-reality generalization gaps. Critical research gaps are identified, including the absence of public benchmark datasets, inadequate handling of temporal multi-scale phenomena, and the persistent challenge of bridging simulated and real-world observations. Future directions should pursue physics-guided machine learning frameworks that integrate domain knowledge with data-driven capabilities, develop explainable artificial intelligence techniques tailored for photometric analysis, and establish standardized evaluation protocols to advance next-generation space object characterization essential for collision avoidance and space traffic management.

Ground-based photometric data of high-orbit targets are essential for attitude estimation and physical characterization, but their quality is degraded by atmospheric turbulence, sky background, and tracking instabilities. Existing methods rely on discrete binary flags or statistical outlier rejection, lacking fine-grained credibility quantification and failing to exploit the physical prior of light curve smoothness. This paper proposes a quality assessment framework that replaces binary labels with continuous credibility scores. The method first segments data into continuous arcs, removes transient edge points, and extracts smooth trends. Then, three credibility factors (elevation angle, arc duration, and local residual robustness) are combined with hard rejection rules to yield a comprehensive score between 0 and 1. Daily and target-level scores are further synthesized for multi-granularity quality comparison. Experiments on real high-orbit photometric data show that the hard rejection ratio is below 3%, credibility distributions align well with observed data quality, and daily scores effectively distinguish good from poor observation nights. The generated credibility can be directly used as sample weights in downstream models, enhancing the reliability of optical data analysis.