# A Railway Network Dataset Incorporating Multi-Type Train Operation Records and Train Scheduling

**Authors:** Jianqing Wu, Xukai Xiao, Yitao Zhou, Bo Du, Jun Shen, Yishan Chen, Bi Wang, Qiang Wu

PMC · DOI: 10.1038/s41597-025-06385-8 · Scientific Data · 2025-12-13

## TL;DR

This paper introduces a comprehensive Italian railway dataset combining train operations and scheduling data to support transportation research.

## Contribution

The paper presents a novel, standardized railway dataset integrating multi-type train operations and scheduling data.

## Key findings

- The dataset includes train records, station locations, mileage, weather, and scheduling data.
- It supports research in spatio-temporal patterns, network analysis, and delay propagation.
- The dataset aids in solving operational challenges like timetable optimization and system resilience.

## Abstract

Train operation data contains valuable information with potential insights, yet the datasets released by railway companies are often unstandardized or incomplete, limiting their direct applicability in research. Publicly available railway network datasets that comprehensively integrate train operation records with scheduling information remain rare. To support research in large-scale complex networks, dynamic systems, and intelligent transportation systems, we present the Italian Railway Network Dataset. This dataset includes operational records of multiple types of trains, station locations, inter-station mileage, weather conditions, and scheduling data. By providing detailed and structured railway data, our dataset facilitates research in diverse areas such as spatio-temporal pattern mining, network topology analysis, and train delay propagation and distribution. Moreover, it offers valuable support for addressing operational challenges in the railway domain, including timetable optimization, system resilience assessment, and advanced scheduling strategies.

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12827336/full.md

## Figures

9 figures with captions in the complete paper: https://tomesphere.com/paper/PMC12827336/full.md

## References

5 references — full list in the complete paper: https://tomesphere.com/paper/PMC12827336/full.md

---
Source: https://tomesphere.com/paper/PMC12827336