Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Isha Jariwala, Xinquan Wang, Bridget Meier, Guanyue Qian, Dipankar Shakya, Mingjun Ying, Homa Nikbakht, Daniel Abraham, Theodore S. Rappaport

TL;DR

The paper presents NYUSIM's transition from MATLAB to Python to support AI-enabled, measurement-driven propagation research across FR1(C) and FR3 frequencies. It preserves physical fidelity while enabling modularity, large-scale data generation, and seamless AI workflow integration through a deterministic/stochastic framework and rigorous verification. Key contributions include the Ant3D 3D antenna format, the AntPat reconstruction module, and FR3 measurement-based modeling, all validated against the original MATLAB implementation and field data. This work establishes a scalable, transparent platform for AI-assisted channel synthesis, parameter inference, and integration with network simulators such as ns-3, accelerating 6G propagation research and system design.

Abstract

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.

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

TL;DR

The paper presents NYUSIM's transition from MATLAB to Python to support AI-enabled, measurement-driven propagation research across FR1(C) and FR3 frequencies. It preserves physical fidelity while enabling modularity, large-scale data generation, and seamless AI workflow integration through a deterministic/stochastic framework and rigorous verification. Key contributions include the Ant3D 3D antenna format, the AntPat reconstruction module, and FR3 measurement-based modeling, all validated against the original MATLAB implementation and field data. This work establishes a scalable, transparent platform for AI-assisted channel synthesis, parameter inference, and integration with network simulators such as ns-3, accelerating 6G propagation research and system design.

Abstract

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.
Paper Structure (15 sections, 4 equations, 3 figures, 1 table)

This paper contains 15 sections, 4 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction and Background
  2. Motivation to Use AI in Simulation
  3. NYUSIM: from MATLAB to Python
  4. NYUSIM Python Framework
  5. Verification and Statistical Validation of NYUSIM Python
  6. Function-to-Function Testing
  7. End-to-End Testing of NYUSIM Python Operation
  8. Implementing 3D Antenna Patterns in NYUSIM
  9. Ant3D Format
  10. 3D Reconstruction of Antenna Patterns
  11. Integration of AntPat module with NYUSIM Python
  12. Interactive Visualization of Antennas in NYUSIM Python
  13. Integration of 3D antenna pattern into Simulation
  14. FR3 Modeling in NYUSIM Python
  15. Conclusion and Future Work

Figures (3)

  • Figure 1: Examples of the AntPat module in NYUSIM Python. (a) Preset commercial antenna patterns (e.g., JMA iV02OMI136 0.9/2.65 GHz and Pasternack PENWAN-137 antennas). (b) Customizable 3GPP-compliant element/array patterns with adjustable parameters.
  • Figure 2: CDF of directional RMS DS for 16.95 GHz. Measurements globec_indoorsicc_infglobec_penetration were conducted using a 1 GHz-bandwidth sliding-correlation channel sounder and directional horn antennas with 20 dBi gain and 15° HPBW.
  • Figure 3: CDF of directional RMS DS for 6.75 GHz. Measurements globec_indoorsicc_infglobec_penetration were conducted using a 1 GHz-bandwidth sliding-correlation channel sounder and directional horn antennas with 15 dBi gain and 30° HPBW.