A Shap-based Analysis of Remote Sensing Indices for Marine Mucilage Detection and Mapping

The marine mucilage outbreak in the Sea of Marmara in Spring 2021 sparked renewed interest in this complex environmental phenomenon and in monitoring the delicate marine ecosystems of our planet. A number of works in the literature have utilized remote sensing spectral indices with and without classification-based approaches in order to detect and map marine mucilage for this outbreak. Recently, SHAP method, often utilized for the purpose of Explainable Artificial intelligence (XAI) has been utilized to highlight that water-related spectral indices have varying contributions in the detection of marine mucilage. This work continues that line of research in incorporating a large number of water, soil, vegetation, and mucilage indices. Preliminary results, presented in this paper, partially support the findings in the literature while still presenting some interesting outcomes and insights.