AI-Driven Radio Wave Propagation From Modeling to Application in 6G and Beyond

Radio propagation modeling is becoming an increasingly important operational component of wireless systems toward 6G and beyond. Future networks require accurate propagation information across wider frequency ranges, three-dimensional and dynamic environments, integrated communication and sensing functions, and repeated evaluation within wireless digital twins.
This book presents a systematic treatment of artificial intelligence for radio propagation modeling while maintaining explicit connections to propagation physics, measurements, and electromagnetic principles. It examines learning-assisted methods for environment and material representation, electromagnetic and ray-tracing acceleration, model calibration, channel prediction and reconstruction, and propagation-based sensing and localization.
Organized into four parts, the book covers the physical, measurement, and machine-learning foundations of propagation modeling; AI-enhanced propagation methods; applications in intelligent transportation, coverage planning, wireless digital twins, sensing, and localization; and emerging topics including model generalization, credibility, computational scaling, integrated sensing and communication, and AI-native wireless systems.
Combining physical principles, learning-assisted methods, and representative case studies, this book provides a unified reference for graduate students, researchers, and engineers working in radio propagation, channel modeling, machine learning for wireless systems, network planning, and integrated sensing and communication.