Domain-specific datasets are the foundation for unleashing artificial intelligence (AI)-driven wireless innovation. Yet existing wireless AI corpora are slow to produce, offer limited modeling fidelity, and cover only narrow scenario types. To address the challenges, we create DeepTelecom, a three-dimension (3D) digital-twin channel dataset. Specifically, a large language model (LLM)-assisted pipeline first builds the third level of details (LoD3) outdoor and indoor scenes with segmentable material-parameterizable surfaces. Then, DeepTelecom simulates full radio-wave propagation effects based on Sionna's ray-tracing engine. Leveraging GPU acceleration, DeepTelecom streams ray-path trajectories and real-time signal-strength heat maps, compiles them into high-frame-rate videos, and simultaneously outputs synchronized multi-view images, channel tensors, and multi-scale fading traces. By efficiently streaming large-scale, high-fidelity, and multimodal channel data, DeepTelecom not only furnishes a unified benchmark for wireless AI research but also supplies the domain-rich training substrate that enables foundation models to tightly fuse large model intelligence with future communication systems.
@article{arxiv.2508.14507,
title = {DeepTelecom: A Digital-Twin Deep Learning Dataset for Channel and MIMO Applications},
author = {Bohao Wang and Zehua Jiang and Zhenyu Yang and Chongwen Huang and Yongliang Shen and Siming Jiang and Chen Zhu and Zhaohui Yang and Richeng Jin and Zhaoyang Zhang and Sami Muhaidat and Merouane Debbah},
journal= {arXiv preprint arXiv:2508.14507},
year = {2025}
}