# 3D Dynamic Radio Map Prediction Using Vision Transformers for Low-Altitude Wireless Networks

arXiv: https://arxiv.org/abs/2511.19019 · HTML: https://mlsanity.com/paper/2511.19019/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction](https://mlsanity.com/paper/2408.08593/) (2024)
- [RME-GAN: A Learning Framework for Radio Map Estimation based on Conditional Generative Adversarial Network](https://mlsanity.com/paper/2212.12817/) (2022)
- [Radio Map Estimation: A Data-Driven Approach to Spectrum Cartography](https://mlsanity.com/paper/2202.03269/) (2022)
- [Accessing From The Sky: A Tutorial on UAV Communications for 5G and Beyond](https://mlsanity.com/paper/1903.05289/) (2019)
- [Learning from Temporal Gradient for Semi-supervised Action Recognition](https://mlsanity.com/paper/2111.13241/) (2021)
- [Radio Map Based 3D Path Planning for Cellular-Connected UAV](https://mlsanity.com/paper/1912.00021/) (2019)
- [Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications](https://mlsanity.com/paper/2009.01423/) (2020)
- [Deep Transfer Learning for Signal Detection in Ambient Backscatter Communications](https://mlsanity.com/paper/2009.05231/) (2020)
- [Learning-based Predictive Beamforming for Integrated Sensing and Communication in Vehicular Networks](https://mlsanity.com/paper/2108.11540/) (2021)
- [Fast and Accurate Cooperative Radio Map Estimation Enabled by GAN](https://mlsanity.com/paper/2402.02729/) (2024)
- [Spatio-temporal Interference Correlation and Joint Coverage in Cellular Networks](https://mlsanity.com/paper/1606.05332/) (2016)
- [Deep Residual Learning-Assisted Channel Estimation in Ambient Backscatter Communications](https://mlsanity.com/paper/2009.07468/) (2020)
- [Location-aware Predictive Beamforming for UAV Communications: A Deep Learning Approach](https://mlsanity.com/paper/2009.07478/) (2020)
- [Deep CLSTM for Predictive Beamforming in Integrated Sensing and Communication-enabled Vehicular Networks](https://mlsanity.com/paper/2209.12368/) (2022)
- [Predictive Precoder Design for OTFS-Enabled URLLC: A Deep Learning Approach](https://mlsanity.com/paper/2212.13651/) (2022)
- [Scalable Predictive Beamforming for IRS-Assisted Multi-User Communications: A Deep Learning Approach](https://mlsanity.com/paper/2211.12644/) (2022)

## Built on by (most cited first, 1 of 1)

- [Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks](https://mlsanity.com/paper/2609.19538/) (2026)

## Abstract (arXiv)

Low-altitude wireless networks (LAWN) are rapidly expanding with the growing deployment of unmanned aerial vehicles (UAVs) for logistics, surveillance, and emergency response. Reliable connectivity remains a critical yet challenging task due to three-dimensional (3D) mobility, time-varying user density, and limited power budgets. The transmit power of base stations (BSs) fluctuates dynamically according to user locations and traffic demands, leading to a highly non-stationary 3D radio environment. Radio maps (RMs) have emerged as an effective means to characterize spatial power distributions and support radio-aware network optimization. However, most existing works construct static or offline RMs, overlooking real-time power variations and spatio-temporal dependencies in multi-UAV networks. To overcome this limitation, we propose a 3D dynamic radio map (3D-DRM) framework that learns and predicts the spatio-temporal evolution of received power. Specially, a Vision Transformer (ViT) encoder extracts high-dimensional spatial representations from 3D RMs, while a Transformer-based module models sequential dependencies to predict future power distributions. Experiments unveil that 3D-DRM accurately captures fast-varying power dynamics and substantially outperforms baseline models in both RM reconstruction and short-term prediction.