AI 中文总结
该研究提出电磁孪生体，以CKM为信道存储器结合场景信息，通过RF补全主干与残差适配器，从稀疏信道证据重构无线状态，在信道增益场补全任务中实现更低RMSE，验证了测量-更新-查询循环与轻量残差校正的有效性。
AI 中文摘要
在大量位置和波束上获取密集信道信息会产生可观的导频和处理开销。无线电地图与信道知识图谱（CKMs）通过复用特定站点的信道信息来降低这种开销，但当有新的测量或环境观测数据可用时，其内容必须刷新。本文提出一种电磁孪生体，它是一种可更新的数字表示，利用稀疏信道证据重构通信查询所需的无线状态。该孪生体不替代无线电地图或CKMs，而是将CKMs作为信道存储器，结合已注册的场景信息，并在每次证据更新后重新生成输出。我们通过从稀疏样本和不完整的平面图中构建二维信道增益场来实例化这一思路。一个学习得到的射频（RF）补全主干网络可恢复主要传播结构，而一个轻量残差适配器则测试冻结的CLIP特征是否提供有用的辅助信息。在仅4%的测量位置且55%的语义对象缺失的情况下，该RF主干网络达到4.44 dB的均方根误差（RMSE），而CKM插值法为8.29 dB，不完整的物理先验法为8.38 dB。残差适配器使RMSE的配对均值降低0.135 dB（95%置信区间：0.100至0.169 dB），但相同容量的随机特征对照与CLIP条件适配器在统计上无显著差异。因此，结果支持测量-更新-查询循环及轻量残差校正，同时避免将校正归因于视觉语义的无根据做法。
英文摘要
Acquiring dense channel information over many locations and beams incurs considerable pilot and processing overhead. Radio maps and channel knowledge maps (CKMs) reduce this overhead by reusing site-specific channel information, but their contents must be refreshed when new measurements or environmental observations become available. This paper introduces an \emph{electromagnetic twin} as an updatable digital representation that uses sparse channel evidence to reconstruct the wireless state requested by communication queries. Rather than replacing radio maps or CKMs, the twin uses a CKM as channel memory, combines it with registered scene information, and regenerates its outputs after each evidence update. We instantiate this idea by completing a two-dimensional channel-gain field from sparse samples and an incomplete floor plan. A learned RF completion backbone recovers the main propagation structure, and a lightweight residual adapter tests whether frozen CLIP features provide useful side information. With $4\%$ measured locations and $55\%$ missing semantic objects, the RF backbone attains $4.44$ dB RMSE, compared with $8.29$ dB for CKM interpolation and $8.38$ dB for an incomplete physics prior. Residual adaptation reduces RMSE by a paired mean of $0.135$ dB (95\% confidence interval: $0.100$--$0.169$ dB), but a same-capacity random-feature control is statistically indistinguishable from the CLIP-conditioned adapter. The results therefore support the measurement--update--query loop and lightweight residual correction, while avoiding an unsupported attribution of the correction to visual semantics.
