What novel AI-driven approach can Dublin’s traffic systems adopt to integrate weather data and improve daily congestion prediction beyond existing studies?

Slattery, John (2025) What novel AI-driven approach can Dublin’s traffic systems adopt to integrate weather data and improve daily congestion prediction beyond existing studies? Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (735kB) | Preview
Preview	PDF (Configuration Manual) Download (919kB) | Preview

Abstract

Existing traffic forecasting methods often rely solely on past traffic flow and do not account for environmental factors. This research instead focuses on strengthening Dublin’s traffic management by forecasting short-term traffic flow using combined meteorological data and machine-learning algorithms. Data from the traffic flow in South Dublin County Council's Smart Dublin system over multiple years was combined with data from Met Éireann on rainfall, air temperature, and other factors.

A data processing pipeline has been implemented to clean and merge both data sources, followed by feature engineering that includes time- and season-related features. The three approaches are Random Forest models, Gradient Boosting models, and hybrids of both methods combined into a single model.

The research makes several contributions to forecasting accuracy while aligning with ethical considerations. The results show that the Hybrid Ensemble model improves prediction accuracy and demonstrates the value of integrating meteorological data into Dublin’s traffic forecasting systems.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hasanuzzaman, Mohammed UNSPECIFIED
Subjects:	T Technology > TE Highway engineering. Roads and pavements Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence D History General and Old World > DA Great Britain > Ireland > Dublin H Social Sciences > HE Transportation and Communications > Urban Transportation G Geography. Anthropology. Recreation > GE Environmental Sciences > Earth sciences > Atmospheric science > Meteorology > Weather
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	09 Sep 2026 09:49
Last Modified:	09 Sep 2026 09:49
URI:	https://norma.ncirl.ie/id/eprint/9915

Actions (login required)

View Item