CSRD2025: A Large-Scale Synthetic Radio Dataset for Spectrum Sensing in Wireless Communications

TL;DR

This paper introduces CSRD, a large-scale synthetic radio dataset generated by a modular simulation platform, to advance AI-based spectrum sensing in wireless communications by providing diverse, realistic RF data.

Contribution

The paper presents the CSRD framework for generating extensive synthetic RF datasets, including a benchmark dataset with over 25 million frames, to support AI research in spectrum sensing.

Findings

CSRD2025 dataset is 10,000 times larger than RML2018.

Includes diverse modulation schemes and realistic channel models.

Facilitates object detection in spectrum analysis.

Abstract

The development of Large AI Models (LAMs) for wireless communications, particularly for complex tasks like spectrum sensing, is critically dependent on the availability of vast, diverse, and realistic datasets. Addressing this need, this paper introduces the ChangShuoRadioData (CSRD) framework, an open-source, modular simulation platform designed for generating large-scale synthetic radio frequency (RF) data. CSRD simulates the end-to-end transmission and reception process, incorporating an extensive range of modulation schemes (100 types, including analog, digital, OFDM, and OTFS), configurable channel models featuring both statistical fading and site-specific ray tracing using OpenStreetMap data, and detailed modeling of realistic RF front-end impairments for various antenna configurations (SISO/MISO/MIMO). Using this framework, we characterize CSRD2025, a substantial dataset benchmark comprising over 25,000,000 frames (approx. 200TB), which is approximately 10,000 times larger than the widely used RML2018 dataset. CSRD2025 offers unprecedented signal diversity and complexity, specifically engineered to bridge the Sim2Real gap. Furthermore, we provide processing pipelines to convert IQ data into spectrograms annotated in COCO format, facilitating object detection approaches for time-frequency signal analysis. The dataset specification includes standardized 8:1:1 training, validation, and test splits (via frame indices) to ensure reproducible research. The CSRD framework is released at https://github.com/Singingkettle/ChangShuoRadioData to accelerate the advancement of AI-driven spectrum sensing and management.