A Machine Learning Framework for Handling Unreliable Absence Label and Class Imbalance for Marine Stinger Beaching Prediction

TL;DR

This paper develops a machine learning framework to predict bluebottle marine stinger presence on beaches, effectively handling class imbalance, unreliable absence data, and class overlap, with Random Forests and synthetic negative data showing the best results.

Contribution

It introduces a novel approach combining data augmentation techniques to address class overlap and unreliable absence labels in marine stinger prediction models.

Findings

SMOTE failed to resolve class overlap

Presence-focused approach effectively handled imbalance

Random Forest with Synthetic Negative Approach was most accurate

Abstract

Bluebottles (\textit{Physalia} spp.) are marine stingers resembling jellyfish, whose presence on Australian beaches poses a significant public risk due to their venomous nature. Understanding the environmental factors driving bluebottles ashore is crucial for mitigating their impact, and machine learning tools are to date relatively unexplored. We use bluebottle marine stinger presence/absence data from beaches in Eastern Sydney, Australia, and compare machine learning models (Multilayer Perceptron, Random Forest, and XGBoost) to identify factors influencing their presence. We address challenges such as class imbalance, class overlap, and unreliable absence data by employing data augmentation techniques, including the Synthetic Minority Oversampling Technique (SMOTE), Random Undersampling, and Synthetic Negative Approach that excludes the negative class. Our results show that SMOTE failed to resolve class overlap, but the presence-focused approach effectively handled imbalance, class overlap, and ambiguous absence data. The data attributes such as the wind direction, which is a circular variable, emerged as a key factor influencing bluebottle presence, confirming previous inference studies. However, in the absence of population dynamics, biological behaviours, and life cycles, the best predictive model appears to be Random Forests combined with Synthetic Negative Approach. This research contributes to mitigating the risks posed by bluebottles to beachgoers and provides insights into handling class overlap and unreliable negative class in environmental modelling.