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.
Yang et al. (Wed,) studied this question.