Programme

HDIP in Data Analytics for Business

Abstract

This research examines Ireland’s air pollution trends and evaluates whether current reductions in PM2.5, PM10, and NO₂ are sufficient to meet the WHO 2021 Air Quality Guidelines by 2040. Using four years of EPA-validated pollutant data (2020–2023), alongside Building Energy Rating (BER) and national transport datasets, the study applies the CRISP-DM methodology to guide analysis, preprocessing, modelling, and evaluation. Extensive data cleaning and alignment were required due to inconsistent station coverage, varying formats, and missing values. Forecasting models—including Random Forest, Gradient Boosting, SVR, and linear regression—were assessed using MSE, R², and trend significance to project pollutant levels across different Irish settlement types. Preliminary findings indicate persistent exceedances of WHO daily and annual limits for PM2.5 and NO₂, driven primarily by solid fuel burning and vehicle emissions, while PM10 generally remains within guideline levels. Results suggest that without accelerated policy and behavioural changes, Ireland is unlikely to meet WHO 2040 targets, particularly in urban regions such as Dublin and large towns. Additional analyses of building energy efficiency and transport behaviour highlight the need for rapid reductions in home-heating emissions and increased public transport uptake. This study underscores the health risks posed by ongoing air pollution—estimated to contribute to 1,600 premature deaths annually in Ireland—and provides modelling insights to support targeted environmental and public-health interventions.

Date of Award

2025

Full Publication Date

2025

Access Rights

open access

Document Type

Capstone Project

Resource Type

thesis

Included in

Data Science Commons

Share

COinS