通信学报2026，Vol.47Issue(3)：112-122,11.DOI:10.11959/j.issn.1000-436x.2026061
基于成本敏感CNN-BiLSTM网络的目标可见性预测方法
Target visibility prediction method based on cost-sensitive CNN-BiLSTM network
摘要
Abstract
To address the low accuracy and insufficient autonomy of the traditional SGP4 model in predicting target vis-ibility under non-perfect ephemeris conditions,a cost-sensitive hybrid network-based method was proposed for predict-ing the visibility of high-dynamic targets in specific regions.This method employed an early fusion of multi-source het-erogeneous data features and constructed a CNN-BiLSTM architecture to comprehensively extract spatial geometric lo-cal features and temporal short-term dependency features.A cost-sensitive learning mechanism was introduced to ad-dress the extreme imbalance in target visibility,enabling accurate prediction of visibility windows in specific regions.The results show that with an extreme imbalance ratio of 1:357,the proposed method achieves a precision of 94.56%and a recall of 97.78%,outperforming existing methods,and provides technical support for space mission planning and colli-sion avoidance warning.关键词
空天目标/空间安全保障/目标可见性预测/深度学习Key words
aerospace target/space safety and security/target visibility prediction/deep learning分类
信息技术与安全科学引用本文复制引用
廖希,蔺瑞甲,郑相全,文凯..基于成本敏感CNN-BiLSTM网络的目标可见性预测方法[J].通信学报,2026,47(3):112-122,11.基金项目
重庆市自然科学基金资助项目(No.CSTB2025YITP-QCRC0045) Chongqing Natural Science Foundation(No.CSTB2025YITP-QCRC0045) （No.CSTB2025YITP-QCRC0045）
