![[2507.14186] A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2507.14186] A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction
Summary
This paper presents a novel framework for predicting low-altitude network coverage using disentangled representation learning, addressing challenges in data scarcity and feature sampling.
Why It Matters
As the low-altitude economy grows, effective network coverage prediction becomes crucial for aerial operations. This framework offers a data-driven solution to improve prediction accuracy, which is vital for optimizing aerial corridors and enhancing communication services.
Key Takeaways
- Introduces a dual strategy combining expert knowledge and disentangled representation learning.
- Addresses challenges of data scarcity and imbalanced feature sampling in low-altitude network coverage.
- Achieves a 7% reduction in prediction error compared to existing algorithms.
- Demonstrates practical accuracy with MAE errors at the 5dB level through real-network validations.
- Highlights the importance of operational parameters in predicting antenna beam patterns.
Computer Science > Networking and Internet Architecture arXiv:2507.14186 (cs) [Submitted on 13 Jul 2025 (v1), last revised 14 Feb 2026 (this version, v2)] Title:A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction Authors:Xiaojie Li, Zhijie Cai, Nan Qi, Chao Dong, Guangxu Zhu, Haixia Ma, Qihui Wu, Shi Jin View a PDF of the paper titled A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction, by Xiaojie Li and 7 other authors View PDF HTML (experimental) Abstract:The expansion of the low-altitude economy has underscored the significance of Low-Altitude Network Coverage (LANC) prediction for designing aerial corridors. While accurate LANC forecasting hinges on the antenna beam patterns of Base Stations (BSs), these patterns are typically proprietary and not readily accessible. Operational parameters of BSs, which inherently contain beam information, offer an opportunity for data-driven low-altitude coverage prediction. However, collecting extensive low-altitude road test data is cost-prohibitive, often yielding only sparse samples per BS. This scarcity results in two primary challenges: imbalanced feature sampling due to limited variability in high-dimensional operational parameters against the backdrop of substantial changes in low-dimensional sampling locations, and diminished generalizability stemming from insufficient data samples. To overcome these obstacles, we introduce a dual strategy comp...