Bridget Meier | Searcharxiv

arXiv2026

NYUSIM: A Roadmap to AI-Enabled Statistical Channel Modeling and Simulation

Integrating artificial intelligence (AI) into wireless channel modeling requires large, accurate, and physically consistent datasets derived from real measurements. Such datasets are essential for training and validating models that learn spatio-temporal channel behavior across frequencies and environments. NYUSIM, introduced by NYU WIRELESS in 2016, generates realistic spatio-temporal channel data using extensive outdoor and indoor measurements between 28 and 142 GHz. To improve scalability and support 6G research, we migrated the complete NYUSIM framework from MATLAB to Python, and are incorporating new statistical model generation capabilities from extensive field measurements in the new 6G upper mid-band spectrum at 6.75 GHz (FR1(C)) and 16.95 GHz (FR3) [1]. The NYUSIM Python also incorporates a 3D antenna data format, referred to as Ant3D, which is a standardized, full-sphere format for defining canonical, commercial, or measured antenna patterns for any statistical or site-specific ray tracing modeling tool. Migration from MATLAB to Python was rigorously validated through Kolmogorov-Smirnov (K-S) tests, moment analysis, and end-to-end testing with unified randomness control, confirming statistical consistency and reproduction of spatio-temporal channel statistics, including spatial consistency with the open-source MATLAB NYUSIM v4.0 implementation. The NYUSIM Python version is designed to integrate with modern AI workflows and enable large-scale parallel data generation, establishing a robust, verified, and extensible foundation for future AI-enabled channel modeling.

eess.SP↗

arXiv2025

Standardized Machine-Readable Point-Data Format for Consolidating Wireless Propagation Across Environments, Frequencies, and Institutions

The necessity of new spectrum for 6G has intensified global interest in radio propagation measurements across emerging frequency bands, use cases, and antenna types. These measurements are vital for understanding radio channel properties in diverse environments, and involve time-consuming and expensive campaigns. A major challenge for the effective utilization of propagation measurement data has been the lack of a standardized format for reporting and archiving results. Although organizations such as NIST, NGA, and 3GPP have made commendable efforts for data pooling, a unified machine-readable data format for consolidating measurements across different institutions and frequencies remains a missing piece in advancing global standardization efforts. This paper introduces a standardized point-data format for radio propagation measurements and demonstrates how institutions may merge disparate campaigns into a common format. This data format, alongside an environmental map and a measurement summary metadata table, enables integration of data from disparate sources by using a structured representation of key parameters. Here, we show the efficacy of the point-data format standard using data gathered from two independent sub-THz urban microcell (UMi) campaigns: 142 GHz measurements at New York University (NYU) and 145 GHz measurements at the University of Southern California (USC). A joint path loss analysis using the close-in path loss model (1 m ref. distance) yields a refined estimate of the path loss exponent (PLE) employing the proposed standard to pool measurements. Other statistics such as RMS delay spread and angular spread are also determined using a joint point-data table. Adopting this simple, unified format will accelerate channel model development, build multi-institutional datasets, and feed AI/ML applications with reliable training data in a common format from many sources.

eess.SP↗