Due to the rapid development of mobile communication and edge computing, mobile multi-hop information systems have been widely applied in many areas such as intelligent transportation, smart agriculture, and intelligent medical treatment. Reconfigurable channel modeling plays an important role in the system design and optimization of mobile multi-hop information systems, as the channel is the medium for the propagation of electromagnetic waves. Being aware of how the channel affects the propagation waves is essential for the design, optimization, and performance analysis of mobile multi-hop information systems. Recently, deep learning has made a breakthrough and reached beyond human-level performances in image recognition, natural language processing, anomaly detection, and wireless communications. To enhance the abilities of information processing and analysis, deep learning-based applications are deployed on edge devices to facilitate the emergence of edge intelligence. Hence, deep learning provides many potential opportunities for reconfigurable channel modeling in mobile multi-hop information systems.

However, deep reconfigurable channel modeling also brings several critical challenges for mobile multi-hop information systems. One large challenge is how to devise deep reconfigurable channel modeling approaches, which can effectively capture the system's spatio-temporal characteristics. This is particularly important for the time-varying channels in the mobile multi-hop information systems when the nodes in the system are moving at a high speed. A second challenge is deep reconfigurable channel estimation and channel state information feedback, which are of vital importance to the system precoding design, transmitter design, and reception schemes design. Another challenge is how to devise an intelligent approach for the system transmitter and receiver design, to deeply exploit the system communication and computing resources.

To address the above major challenges in deep reconfigurable channel modeling for mobile multi-hop information systems, this Special Issue aims to provide a comprehensive overview of deep learning and to generate more ideas on reconfigurable channel modeling for mobile multi-hop information systems. This Special Issue aims to bring together researchers from academia, industry, and governmental agencies to promote the research and development that pertain to this cutting-edge research topic. We welcome both original research and review papers.

Potential topics include but are not limited to the following:

• Deep reconfigurable channel modeling
• Intelligent waveform design
• Data and model-driven channel estimation
• Advanced channel prediction
• Deep channel state information feedback
• Advanced signal modulation
• Intelligent transmitter design
• Deep learning-based reception scheme
• Deep learning, federated learning
• Internet of things, smart cities
• Applications of deep channel modeling
• Hardware implementation of reconfigurable channel modeling