Loading
Life sciences · Preprint
arXiv · September 10, 2026
Early or partial results. Treat as a signal, not a conclusion.
This is a single-centre, unvalidated machine learning study showing that domain-engineered weather categories outperform raw meteorological features for predicting train delays at Oulu station. The work is exploratory and demonstrates technical feasibility within one location; external validation and comparison to operational baselines are absent, and the study has not undergone peer review.
Single-centre observational machine learning model evaluation. Train delay records from Oulu central station, Finland, linked to observations from approximately 200 wireless-connected meteorological stations operated by the Finnish Meteorological Institute.. Intervention: Domain-engineered weather category features (hierarchical classifications such as Blizzard, Heavy Snow, Extreme Cold) as model inputs. Compared with: Full weather features and instant weather observations only, evaluated with the same XGBoost model. n = 101,146. Oulu central station, Finland; Arctic region with extreme temperatures and heavy precipitation..
Category-based weather features achieved R² of 0.78, RMSE of 8.5 minutes, and MAE of 3.7 minutes at Oulu station Category-based approach showed 11% R² improvement and 10% error reduction over full weather features and instant observations
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
A single-centre machine learning model evaluation on observational data with no clinical outcome, comparator arm, or external validation; demonstrates technical feasibility but requires independent testing before operational deployment.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Reliable railway operations depend increasingly on real-time environmental intelligence delivered through wireless sensor infrastructures, a capability that 6G networks will substantially enhance through integrated sensing and edge computing. Adverse weather, particularly in Arctic regions with extreme temperatures and heavy precipitation, remains a leading cause of train delays, yet most prediction approaches rely on raw meteorological inputs without exploiting domain-informed feature engineering. This paper investigates machine learning for train delay prediction using the Finland Integrated Train-Weather (FI-TW) dataset, which fuses railway operational records with observations from the Finnish Meteorological Institute's nationwide sensor network of approximately 200 stations communicating over wireless links. We evaluate three feature configurations using XGBoost at Oulu central station (101,146 observations): full weather features, instant weather observations only, and derived weather category scenarios. The category-based approach, employing hierarchical classifications such as Blizzard, Heavy Snow, and Extreme Cold, achieved an R^2 of 0.78, root mean squared error of 8.5 minutes, and mean absolute error of 3.7 minutes, representing an 11% R^2 improvement and 10% error reduction over alternative configurations. These results demonstrate that compact, domain-informed features derived from sensor streams outperform raw meteorological observations, offering bandwidth-efficient representations suitable for edge deployment over current and emerging wireless infrastructures.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.