# Deciphering Region-Level Signatures from Latency Measurements in LEO Satellite Internet

arXiv: https://arxiv.org/abs/2606.29324 · HTML: https://mlsanity.com/paper/2606.29324/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 28 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [WetLinks: a Large-Scale Longitudinal Starlink Dataset with Contiguous Weather Data](https://mlsanity.com/paper/2402.16448/) (2024)
- [A Multifaceted Look at Starlink Performance](https://mlsanity.com/paper/2310.09242/) (2023)
- [Statistical Characterization and Prediction of E2E Latency over LEO Satellite Networks](https://mlsanity.com/paper/2601.08439/) (2026)
- [Democratizing LEO Satellite Network Measurement](https://mlsanity.com/paper/2306.07469/) (2023)
- [Closing the Performance and Management Gaps with Satellite Internet: Challenges, Approaches, and Future Directions](https://mlsanity.com/paper/2401.07842/) (2024)
- [Investigating Web Content Delivery Performance over Starlink](https://mlsanity.com/paper/2510.13710/) (2025)

## Abstract (arXiv)

Low-Earth orbit (LEO) satellite Internet has become an indispensable infrastructure that provide growing coverage for global users. Despite extensive measurement efforts, the principles underlying region-level performance characteristics remain insufficiently understood, limiting the ability to identify region-specific latency signatures under dynamic network conditions. In this paper, we formulate the problem of region-level latency characterization using Starlink round-trip time (RTT) measurements from the public LENS dataset. We then propose a hierarchical analytical framework that transforms raw RTT sequences into multi-scale statistical features for cross-region comparison. Using data from five geographically representative regions, we demonstrate that latency differences are strongly associated with deployment factors, particularly infrastructure availability and Starlink dish-to-Point-of-Presence distance. Mutual information analysis identifies minimum RTT as the most discriminative feature, which is further supported by XGBoost-based feature importance. The proposed model well achieves 83% accuracy on short-term data. However, its performance degrades over longer periods, indicating limited temporal generalization and motivating the need for adaptive models and feature representations for long-term performance in the future.