The Vienna 4G/5G Drive-Test Dataset

Vienna 4G/5G Drive-Test Dataset is a large-scale open dataset of cellular measurements collected across Vienna, Austria. It combines passive scanner measurements with active smartphone (UE) logs, providing complementary network-side and user-side views of deployed Long Term Evolution (LTE) and 5G New Radio (5G NR) radio access networks. All measurements are georeferenced (WGS84/EPSG:4326) and cover diverse urban and suburban environments, enabling spatially resolved studies of radio propagation, coverage, and performance. In addition to measurements, the dataset provides inferred deployment descriptors for a representative subset of cells, including estimated site locations, sector orientations, and antenna heights derived from measurement-based inference (e.g., timing-advance–based localization and signal-strength analysis). LTE measurements can be associated with inferred deployment metadata via standardized network-reported identifiers. For 5G NR handset measurements collected in non-standalone (NSA) mode, where physical NR identifiers are not exposed, the dataset includes auxiliary dataset-internal identifiers (cell_id_dummy, gnb_id_dummy) where reliable estimates are available. To support environment-aware analysis and digital-twin workflows, the repository also includes a building and terrain model of Vienna released by the City of Vienna under CC BY 4.0 (see city_model/README.md for attribution and details). Together, the measurement data, inferred deployment descriptors, and environmental context enable geometry-conditioned and environment-aware machine learning tasks (e.g., radio map estimation, propagation modeling, and digital-twin calibration), as well as benchmarking for coverage analysis and base station localization. Contents (high level) Scanner measurements (LTE & 5G NR): snapshot-based detections with per-cell metrics; CINR is used only for LTE scanner, while other quality ratios are reported as SINR. Smartphone/UE logs (LTE & 5G NR NSA): connected-mode measurements with radio, mobility, and QoS-relevant KPIs. Estimated cell information: inferred positions, orientations, and antenna heights (subset coverage). City model (optional): building and terrain rasters for Vienna (separately documented). License Measurement data, inferred deployment descriptors, and repository documentation: Creative Commons Attribution 4.0 International (CC BY 4.0). Building and terrain model: CC BY 4.0, attributed to Stadtvermessung Wien / Open Government Data Wien (see city_model/README.md). Citation Please cite the dataset DOI and the associated journal paper: Dataset (this Zenodo record): DOI: [auto-generated by Zenodo] Paper: [to be added after publication]