Predicting the likelihood of the need to launch a RNLI rescue boat in Ireland based on the Weather and Bank Holidays

Fryer, Elmarie (2021) Predicting the likelihood of the need to launch a RNLI rescue boat in Ireland based on the Weather and Bank Holidays. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (717kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

This paper investigates the relationship between the need to launch a lifeboat and the weather. The ability to predict when a rescue boat will have to be launch will greatly assist organisations, such as the RNLI, that are dependent on volunteers for their efforts. Being able to predict when a launch is most likely will assist volunteers in planning personal activities, and add to the local, institutional knowledge currently used by volunteers. The impact of the volume of water users, as represented by Bank Holiday weekends, is also considered.

Data used include Irish weather data from Met Eireann, Incident data from the RNLI, Irish Bank Holidays, Seasonality, and a Calendar and the architecture used include an Azure SQL Server and RapidMiner hosted on an Azure Virtual Machine. The project was executed on Cloud based technologies to reflect the reality of geographically dispersed volunteers.

Nine predictive models are evaluated in terms of Accuracy, Class Prediction and the Cost to Compute. Gradient Boosted Trees and Deep Learning are found to be the best fit/ models deployed. Further research is also identified taking gender, skill level and the types of incidents into account. This will inform policy making for water safety.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Clara Chan
Date Deposited:	25 Nov 2021 16:40
Last Modified:	25 Nov 2021 16:40
URI:	https://norma.ncirl.ie/id/eprint/5148

Actions (login required)

View Item