Analysing the impact of diesel trains on air quality in a semi-enclosed railway station through mixed monitoring methods and XGBoost modelling

Read full text Summarise with VIRAT
Authors: Shanmuga Priyan, Muireann Kearney, Neha Jacob, Yuxuan Guo, Madhavan Vasudevan, Aonghus McNabola, Brian Broderick, Brian Caulfield, Margaret O’Mahony, John Gallagher
Cited by: 0
References: 24

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study assessed air quality in a semi-enclosed train station using both personal and fixed monitoring and applied eXtreme Gradient Boosting (XGBoost) modelling to identify key factors influencing pollutant levels. The investigation also examined the effects of train idling time and engine speed on fuel consumption and pollutant emissions. Personal monitoring showed the average PM 2 . 5 concentrations of 17–137 μg/m 3 during active train operations, with higher levels observed in enclosed platforms and when diesel multiple unit (DMU) trains were present. Continuous fixed monitoring captured 24-h average concentrations of 3.18–32.56 μg/m 3 for PM 2 . 5 , with DMU-dominated platforms exceeding WHO PM 2 . 5 limits during 90% of the monitoring period. The 24-h average NO 2 levels ranged from 135.6 to 169.8 μg/m 3 , with 11–15% of hourly values in a month exceeding the EU hourly limit. The XGBoost model demonstrated a moderate fit (RMSE: 15.12 μg/m 3 , R 2 : 0.61) and identified ambient temperature and average train idling time as the most influential predictors of NO 2 levels. Partial dependence analysis indicated that reducing average idling time by 2 min could reduce NO 2 concentrations by approximately 2.5 μg/m 3 per train. Operational analysis suggests shutting down engines when the next operation is more than 30 min, restarting them 15 min before departure, and maintaining idle speeds below 600 RPM. These measures could save over 7,000 L of diesel per month, reduce fuel consumption by 40–45%, and lower NO x and PM emissions by around 54%, offering actionable strategies to improve station air quality.

Fields of Study & Subjects

Air Quality and Health Impacts Air Quality Monitoring and Forecasting Vehicle emissions and performance

Publication details

Journal / source
Environmental Pollution
Volume
397
Pages
128029–128029
Publication date
27 March 2026
Language
EN