Shellfish farm closure prediction and cause identification using machine learning methods

Abstract

Shellfish farms are needed to be closed if they are contaminated during their production as otherwise it may lead to serious health hazard. The authorities monitor a number of water quality variables to check the health of shellfish farms and to decide on the closure of the farms. The research presented in this paper aims to automate this process by developing novel algorithms to identify the cause of closure and also predicting the closure. As the frequency of closure is relatively very small, the labelled data sets are imbalanced in nature. We have developed a novel ensemble feature ranking algorithm that explicitly deals with class imbalance problem and identifies the cause of closure. We have also presented a class balancing ensemble classifier to predict shellfish farm closure. The class balancing ensemble classifier predicts closure/opening with as high as 71.69% accuracy and achieves best balancing act with decision tree base classifier in 75% locations. Rain and salinity are found to be the key causes of closure and the causality depends of the properties of the locations.