A Digital Twin-Driven Computation and Analysis Framework for Low-Altitude Airspace

To address key challenges in low-altitude airspace management, such as high dynamic complexity, significant safety risks, and information fragmentation, a digital twin-based methodology for low-altitude airspace computation and analysis is proposed in this paper. First, a four-layer digital twin system architecture is established. High-fidelity digital twin mapping of the low-altitude airspace is achieved through the integration of multi-source heterogeneous data, the application of unified spatio-temporal representation, the implementation of dynamic evolution modeling, and the facilitation of bidirectional physical-virtual closed-loop interaction. Second, innovative intelligent algorithms, including a bidirectional GRU-Seq2Seq trajectory prediction model and a Kalman filter-based error compensation mechanism, are incorporated. These components form a comprehensive technical framework that supports quantitative airspace resource evaluation, real-time trajectory analysis, and conflict prediction and early warning. Finally, experimental validation is conducted across three scenarios: single-target conventional flight, multi-target collaborative flight, and extreme weather interference. The results indicate that, compared with the conventional geometric twin approach, the proposed method achieves a 37.2% reduction in trajectory deviation, a 62.5% improvement in conflict warning accuracy, and a 28.6% enhancement in site selection safety. Furthermore, it is shown to outperform traditional methods across five core performance metrics, including computational efficiency and trajectory accuracy, which further confirms its strong suitability for supporting the high-quality development of the low-altitude economy.