Physics-informed line-of-sight learning for scalable deterministic channel modeling
This addresses the scalability issue of ray tracing for area-wide deployment in wireless communication, offering a domain-specific incremental improvement.
The paper tackles the bottleneck of line-of-sight region determination in deterministic channel modeling by proposing D$^2$LoS, a physics-informed neural network that reformulates dense pixel-level prediction into sparse vertex-level tasks, achieving 3.28 dB mean absolute error in received power and accelerating visibility computation by over 25×.
Deterministic channel modeling maps a physical environment to its site-specific electromagnetic response. Ray tracing produces complete multi-dimensional channel information but remains prohibitively expensive for area-wide deployment. We identify line-of-sight (LoS) region determination as the dominant bottleneck. To address this, we propose D$^2$LoS, a physics-informed neural network that reformulates dense pixel-level LoS prediction into sparse vertex-level visibility classification and projection point regression, avoiding the spectral bias at sharp boundaries. A geometric post-processing step enforces hard physical constraints, yielding exact piecewise-linear boundaries. Because LoS computation depends only on building geometry, cross-band channel information is obtained by updating material parameters without retraining. We also construct RayVerse-100, a ray-level dataset spanning 100 urban scenarios with per-ray complex gain, angle, delay, and geometric trajectory. Evaluated against rigorous ray tracing ground truth, D$^2$LoS achieves 3.28~dB mean absolute error in received power, 4.65$^\circ$ angular spread error, and 20.64~ns delay spread error, while accelerating visibility computation by over 25$\times$.