Data analysis of sea water quality and climatological factors

• Main Author: Kwok, Chin Kiat
• Other Authors: Wong Kin Shun, Terence
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering
• Online Access: https://hdl.handle.net/10356/176480
• Institution: Nanyang Technological University

Endangering marine life, disruption of local economies, and human health are some of the effects of harmful algae blooms in many parts of the world. In Hong Kong, these events are particularly concerning because of the region’s dense population and heavy reliance on seafood. Several research papers regarding the use of prediction models to estimate water quality have been published for various locations around the world, namely in the United States and Hong Kong. In Hong Kong, empirical analysis has been done using deep neural network models with 3 to 12 layers have been deployed to 1990-2016 data from the Hong Kong Environmental Protection Department. This paper aims to evaluate the predictability of E. coli using a variety of models in the selected affected areas of Hong Kong. The objectives were to identify relevant factors and variables affecting the widespread growth of harmful algae blooms and conclude on the best model for the prediction of E. coli using various quantifying tools to check the fit of the model for our use case.