Integrating Meteorological and Operational Data: A Novel Approach to Understanding Railway Delays in Finland

TL;DR

This work addresses the lack of integrated weather-data for railway analysis by introducing the first public Finnish dataset that merges Digitraffic operational data with synchronized FMI meteorological observations from 2018–2024, spanning ~38.5 million records over a 5,915 km network. It implements a robust spatial-temporal merging pipeline using Haversine-based proximity and nearest-temporal matching, with extensive preprocessing, missing-data strategies, and cyclical temporal encodings to create a machine-learning-ready resource containing 28 engineered features. A baseline XGBoost model on station-specific delay (differenceInMinutes_eachStation_offset) achieves an MAE of 2.73 minutes, demonstrating strong predictive potential and illustrating the dataset’s value for delay prediction, weather impact assessment, and infrastructure vulnerability mapping. The dataset enables researchers to explore weather-driven reliability, seasonal patterns, and route-specific dynamics, with data and code openly accessible on Kaggle for broad reuse and extended analyses.

Abstract

Train delays result from complex interactions between operational, technical, and environmental factors. While weather impacts railway reliability, particularly in Nordic regions, existing datasets rarely integrate meteorological information with operational train data. This study presents the first publicly available dataset combining Finnish railway operations with synchronized meteorological observations from 2018-2024. The dataset integrates operational metrics from Finland Digitraffic Railway Traffic Service with weather measurements from 209 environmental monitoring stations, using spatial-temporal alignment via Haversine distance. It encompasses 28 engineered features across operational variables and meteorological measurements, covering approximately 38.5 million observations from Finland's 5,915-kilometer rail network. Preprocessing includes strategic missing data handling through spatial fallback algorithms, cyclical encoding of temporal features, and robust scaling of weather data to address sensor outliers. Analysis reveals distinct seasonal patterns, with winter months exhibiting delay rates exceeding 25\% and geographic clustering of high-delay corridors in central and northern Finland. Furthermore, the work demonstrates applications of the data set in analysing the reliability of railway traffic in Finland. A baseline experiment using XGBoost regression achieved a Mean Absolute Error of 2.73 minutes for predicting station-specific delays, demonstrating the dataset's utility for machine learning applications. The dataset enables diverse applications, including train delay prediction, weather impact assessment, and infrastructure vulnerability mapping, providing researchers with a flexible resource for machine learning applications in railway operations research.

Figures (8)

• Figure 1: Aggregated Normalized Delays by month (2018-2024).
• Figure 2: Delay in minutes grouped by.
• Figure 3: Average delays by week.
• Figure 4: Train stations with nearest meteorological stations across the Finnish railway network.
• Figure 5: Flowchart of the processing steps.