DeepTelecom: A Digital-Twin Deep Learning Dataset for Channel and MIMO Applications

2025-08-20

AI Summary

Existing wireless AI datasets suffer from low generation efficiency, insufficient channel modeling fidelity, and limited scenario coverage, hindering AI-driven wireless communications research. To address these limitations, this paper proposes an LLM-assisted LoD3-level 3D digital twin modeling framework that tightly integrates the Sionna ray-tracing engine with a GPU-accelerated real-time simulation pipeline. This enables, for the first time, synchronized high-frame-rate generation of channel tensors, multi-view images, and dynamic fading trajectories. The resulting high-fidelity, large-scale, multimodal channel dataset comprehensively captures electromagnetic wave propagation characteristics across representative indoor and outdoor scenarios, supporting key tasks such as MIMO system design and channel estimation. It establishes the first unified benchmark for wireless AI and lays the foundation for training and evaluating communication-oriented large language models.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Creating high-fidelity wireless channel datasets for AI
• Overcoming limited scenario coverage in existing datasets
• Generating multimodal channel data for foundation models

Innovation

• LLM-assisted pipeline builds LoD3 scenes
• Ray-tracing engine simulates radio-wave propagation
• GPU acceleration streams multimodal channel data