Comparative Analysis of Machine Learning and Deep Learning Models for Water Potability Prediction

Maniga, Pooja Sree (2024) Comparative Analysis of Machine Learning and Deep Learning Models for Water Potability Prediction. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (617kB) | Preview

Abstract

Water is one of the most important human needs, but with the rising incidences of waterborne diseases, there is a need for an efficient method of monitoring the water quality. Current approaches for evaluating the potability of water are time-consuming and may not be applicable in real-time. This research focuses on the following gaps and limitations in the prior research to examine the effectiveness of machine learning (ML) and deep learning (DL) models. The performance under different conditions was tested on two datasets: a dataset of 300,000 samples and low sampled and class imbalanced dataset of only 3,000 samples. Machine learning models like XGBoost and Random Forest along with various deep learning models like TabNet were used, while feature scaling, one-hot encoding, and handling missing values were done for the dataset. These findings showed that ML models, especially XGBoost, were more accurate with 97% and efficient than DL in predicting the outcomes because of their suitability in managing structured data. Although some DL models such as TabNet used provide good results, these models raise several problems in terms of their computational load and the required volume of data. This study compares traditional ML methods with state-of-the-art DL techniques in a systematic manner to provide best practices for water quality data.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Anu UNSPECIFIED
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	03 Sep 2025 13:37
Last Modified:	03 Sep 2025 13:37
URI:	https://norma.ncirl.ie/id/eprint/8744

Actions (login required)

View Item