Exploring the Impact of Weather on Flight Delays

Kassa, Vasanth Babu (2025) Exploring the Impact of Weather on Flight Delays. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The problem of weather interference greatly affects the global aviation operations, resulting in huge financial losses and discontent among passengers. The topic of this research is the influence of meteorological conditions on flight delay and the effectiveness of the machine learning model in predicting flight delays. The study made use of a large dataset of 1,936,758 flight records (including 30 features) by systematically pre-processing the data, such as by strategic imputation of 689,270 missing values and class balancing using SMOTE. The numerous widely used machine learning classifiers, Logistic Regression, Support Vector Machine, Random Forest, and XGBoost, were compared. The measures utilised were accuracy, precision, recall, F1-score, and ROC-AUC rates. Findings show XGBoost to be the best model with an accuracy of 98.45%, ROC-AUC of 0.99%, precision of 90.12%, and F1-score of 83.78%, which is better than SVM (97.26%), Random Forest (95.69%), and Logistic regression (93.70%). Weather delays were statistically found to be as high as 2.39 minutes, with higher outliers that were 1,932 minutes. These results confirm that gradient boosting algorithms are more effective predictive models of weather-related flight delays, and airlines need to rely on them to have a solid decision support model designed to handle proactive delays and improve operational resiliency.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rifai, Hicham UNSPECIFIED
Subjects:	H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Aviation Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning 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:	07 Sep 2026 13:26
Last Modified:	07 Sep 2026 13:26
URI:	https://norma.ncirl.ie/id/eprint/9868

Actions (login required)

View Item