# WetLinks: a Large-Scale Longitudinal Starlink Dataset with Contiguous Weather Data

arXiv: https://arxiv.org/abs/2402.16448 · HTML: https://mlsanity.com/paper/2402.16448/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2024.

## Built on by (most cited first, 4 of 4)

- [Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches](https://mlsanity.com/paper/2507.14633/) (2025)
- [An Efficient and Generalizable Transfer Learning Method for Weather Condition Detection on Ground Terminals](https://mlsanity.com/paper/2511.00211/) (2025)
- [Deciphering Region-Level Signatures from Latency Measurements in LEO Satellite Internet](https://mlsanity.com/paper/2606.29324/) (2026)
- [A GAN-Based Framework for Robust Data Synthesis in Satellite Internet Observations](https://mlsanity.com/paper/2607.24790/) (2026)

## Abstract (arXiv)

Low Orbit Satellite (LEO) networks such as Starlink promise Internet access everywhere around the world. In this paper, we present WetLinks - a large and publicly available trace-based dataset of Starlink measurements. The measurements were concurrently collected from two European vantage points over a span of six months. Consisting of approximately 140,000 measurements, the dataset comprises all relevant network parameters such as the upload and download throughputs, the RTT, packet loss, and traceroutes. We further augment the dataset with concurrent data from professional weather stations placed next to both Starlink terminals. Based on our dataset, we analyse Starlink performance, including its susceptibility to weather conditions. We use this to validate our dataset by replicating the results of earlier smaller-scale studies. We release our datasets and all accompanying tooling as open data. To the best of our knowledge, ours is the largest Starlink dataset to date.